Map drawing method, device and computer readable storage medium

Abstract

Embodiments of the present application disclose a kind of mapping method, device and computer readable storage medium, can be applied to cloud technology, artificial intelligence, wisdom traffic, various scenes such as auxiliary driving;By obtaining original map road network and historical trajectory point;According to the position information of historical trajectory point, the candidate road section that historical trajectory point matches is identified in road section;Based on the distance between historical trajectory point and the connectivity of original map road network, transition probability is calculated, and based on the distance between historical trajectory point and candidate road section, emission probability is calculated;According to transition probability and emission probability, target road section is filtered out in candidate road section;Based on the path information between historical trajectory point and the transition probability of historical trajectory point to target road section, the missing road section that exists between historical trajectory point is determined;According to missing road section, original map road network is updated to draw, and target map road network is obtained.Therefore, the accuracy of map drawing is improved, and the efficiency of map drawing is improved.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to a map drawing method, apparatus, and computer-readable storage medium. Background Technology

[0002] In recent years, with the rapid development of internet technology, map products have been widely used, for example, in map navigation and intelligent transportation. However, during map creation, incomplete road network data collection technology or quality control issues can easily lead to missing roads in the generated maps, especially short roads such as entrances / exits, ramps, and connecting roads, which are often difficult to spot. Therefore, existing technologies mostly supplement the missing road network by performing a difference analysis between the road network image on the map and the actual trajectory image. Based on the difference result, roads whose trajectories exist on the map but are not part of the road network are extracted again to fill in the missing road network in the map.

[0003] Research and practice on existing technologies have revealed that, due to the short length, dense track points, and high overlap with existing road networks, the existing map drawing methods that supplement missing road networks by subtracting the images of the road network and the track images cannot accurately identify short roads, resulting in low map drawing accuracy and consequently low map drawing efficiency. Summary of the Invention

[0004] This application provides a map drawing method, apparatus, and computer-readable storage medium, which can improve the accuracy of map drawing and thus enhance map drawing efficiency.

[0005] This application provides a map drawing method, including:

[0006] Obtain the original map road network and historical trajectory points, wherein the original map road network includes at least one road segment;

[0007] Based on the location information of the historical trajectory points, candidate road segments matching the historical trajectory points are identified in the road segment;

[0008] Based on the distance between the historical trajectory points and the connectivity of the original map road network, the transfer probability of the historical trajectory point moving to the candidate road segment is calculated, and based on the distance between the historical trajectory point and the candidate road segment, the emission probability of matching the historical trajectory point to the candidate road segment is calculated.

[0009] Based on the transfer probability and the emission probability, target road segments that match the historical trajectory points are selected from the candidate road segments;

[0010] Based on the path information between the historical trajectory points and the transition probability from the historical trajectory points to the target road segment, the missing road segments between the historical trajectory points are determined.

[0011] The original map road network is drawn and updated based on the missing road segments to obtain the target map road network.

[0012] Accordingly, embodiments of this application provide a map drawing apparatus, including:

[0013] The acquisition unit is used to acquire the original map road network and historical trajectory points, wherein the original map road network includes at least one road segment;

[0014] The identification unit is used to identify candidate road segments matching the historical trajectory points in the road segment based on the location information of the historical trajectory points;

[0015] The calculation unit is used to calculate the transfer probability of the historical trajectory point to the candidate road segment based on the distance between the historical trajectory points and the connectivity of the original map road network, and to calculate the emission probability of matching the historical trajectory point to the candidate road segment based on the distance between the historical trajectory point and the candidate road segment.

[0016] A filtering unit is used to filter out target road segments that match the historical trajectory points from the candidate road segments based on the transfer probability and the emission probability.

[0017] The determining unit is used to determine the missing road segments that exist between the historical trajectory points based on the path information between the historical trajectory points and the transition probability from the historical trajectory points to the target road segment;

[0018] The drawing unit is used to draw and update the original map road network based on the missing road segments to obtain the target map road network.

[0019] In one embodiment, the determining unit includes:

[0020] The road segment missing probability calculation subunit is used to calculate the road segment missing probability corresponding to the historical trajectory point based on the path information between the historical trajectory points and the transfer probability from the historical trajectory point to the target road segment;

[0021] The missing road segment identification subunit is used to identify missing road segments that exist between the historical trajectory points based on the road segment missing probability.

[0022] In one embodiment, the road segment missing probability calculation subunit includes:

[0023] The target planning path distance identification module is used to identify the target planning path distance between the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point based on the connectivity relationship in the original map road network;

[0024] The target trajectory path distance calculation module is used to calculate the target trajectory path distance between the historical trajectory points and the associated trajectory points based on the position information of the historical trajectory points and the associated trajectory points.

[0025] The road segment missing probability calculation module is used to obtain the target transfer probability of the historical trajectory point to the target road segment based on the associated trajectory point, and to calculate the road segment missing probability corresponding to the historical trajectory point based on the target transfer probability, the target planned path distance and the direct path distance.

[0026] In one embodiment, the target planning path distance identification module includes:

[0027] The determination submodule is used to determine the projection point of the historical trajectory point in the target road segment and the associated projection point corresponding to the historical trajectory point in the original map road network. The associated projection point is the projection point of the associated trajectory point of the historical trajectory point in the corresponding associated target road segment.

[0028] The identification submodule is used to identify the planned path from the associated projection point to the projection point based on the connectivity in the original map road network;

[0029] The calculation submodule is used to calculate the target planned path distance from the associated projection point to the projection point based on the planned path.

[0030] In one embodiment, the computing unit includes:

[0031] The trajectory path distance calculation subunit is used to calculate the trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point.

[0032] The planned path distance identification subunit is used to identify the planned path distance between the historical trajectory points and associated trajectory points based on the connectivity in the original map road network;

[0033] The transfer probability calculation subunit is used to calculate the transfer probability of the historical trajectory point transferring to the candidate road segment based on the trajectory path distance and the planned path distance.

[0034] In one embodiment, the computing unit includes:

[0035] The projection distance calculation subunit is used to identify the trajectory projection point of the historical trajectory point in the candidate road segment in the original map road network, and to calculate the projection distance from the historical trajectory point to the trajectory projection point.

[0036] The emission probability calculation subunit is used to obtain the system measurement error and, based on the system measurement error and the projection distance, calculate the emission probability of matching the historical trajectory point to the candidate road segment.

[0037] In one embodiment, the identification unit includes:

[0038] Construct sub-units to construct a tree diagram structure corresponding to the original map road network based on the road segments distributed in the original map road network;

[0039] A sub-unit is generated to generate a search area corresponding to the historical trajectory point in the tree structure based on the location information of the historical trajectory point.

[0040] The traversal subunit is used to traverse the tree structure according to the search area to obtain the candidate road segments corresponding to the historical trajectory points.

[0041] In one embodiment, the filtering unit includes:

[0042] The weight acquisition subunit is used to acquire the transition probability and the probability weight corresponding to the emission probability;

[0043] A weighting subunit is used to weight the transition probability and the emission probability based on the probability weights, respectively;

[0044] The filtering subunit is used to fuse the weighted transition probability and emission probability, and filter out the target road segment from the candidate road segments according to the fusion result corresponding to the candidate road segment.

[0045] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the map drawing methods provided in embodiments of this application.

[0046] Furthermore, this application also provides a computer device, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the map drawing method provided in this application.

[0047] This application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the map drawing method provided in this application.

[0048] This application embodiment obtains an original map road network and historical trajectory points, the original map road network including at least one road segment; based on the location information of the historical trajectory points, candidate road segments matching the historical trajectory points are identified within the road segments; based on the distance between historical trajectory points and the connectivity of the original map road network, the transfer probability of historical trajectory points moving to candidate road segments is calculated, and based on the distance between historical trajectory points and candidate road segments, the emission probability of matching historical trajectory points to candidate road segments is calculated; based on the transfer probability and emission probability, target road segments matching historical trajectory points are selected from the candidate road segments; based on the path information between historical trajectory points and the transfer probability from historical trajectory points to target road segments, missing road segments existing between historical trajectory points are determined; the original map road network is drawn and updated based on the missing road segments to obtain the target map road network. In this way, by calculating the transition probability and emission probability corresponding to historical trajectory points, the target road segment matching the historical trajectory points is determined in the original map road network. Based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments, the missing road segments between historical trajectory points are determined. Based on the determined missing road segments, the original map road network is drawn and updated, supplementing the missing road segments in the original map road network, improving the accuracy of map drawing, and thus improving map drawing efficiency. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram illustrating an implementation scenario of a map drawing method provided in this application.

[0051] Figure 2 This is a flowchart illustrating a map drawing method provided in an embodiment of this application;

[0052] Figure 3 This is a schematic diagram illustrating the specific process of a map drawing method provided in an embodiment of this application;

[0053] Figure 4This is a schematic diagram of a tree structure for a map drawing method provided in an embodiment of this application;

[0054] Figure 5a This is a schematic diagram of a map drawing method provided in an embodiment of this application;

[0055] Figure 5b This is a schematic diagram of path information for a map drawing method provided in an embodiment of this application;

[0056] Figure 6 This is another schematic flowchart of a map drawing method provided in an embodiment of this application;

[0057] Figure 7 This is a schematic diagram of the structure of the map drawing device provided in the embodiments of this application;

[0058] Figure 8 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0059] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] This application provides a map drawing method, apparatus, and computer-readable storage medium. The map drawing apparatus can be integrated into a computer device, which may be a server or a terminal, etc.

[0061] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN) acceleration services, and big data and artificial intelligence platforms. The terminal can include, but is not limited to, mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, and aircraft. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0062] Please see Figure 1 Taking the integration of map-making devices into computer equipment as an example, Figure 1This is a schematic diagram illustrating an implementation scenario of the map drawing method provided in this application. The computer device can be a server or a terminal. The computer device can acquire an original map road network and historical trajectory points. The original map road network includes at least one road segment. Based on the location information of the historical trajectory points, candidate road segments matching the historical trajectory points are identified within the road segments. Based on the distance between historical trajectory points and the connectivity of the original map road network, the transfer probability of historical trajectory points moving to candidate road segments is calculated, and based on the distance between historical trajectory points and candidate road segments, the emission probability of matching historical trajectory points to candidate road segments is calculated. Based on the transfer probability and emission probability, target road segments matching historical trajectory points are selected from the candidate road segments. Based on the path information between historical trajectory points and the transfer probability from historical trajectory points to target road segments, missing road segments between historical trajectory points are determined. The original map road network is drawn and updated based on the missing road segments to obtain the target map road network.

[0063] It should be noted that the embodiments of the present invention can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, and assisted driving. Figure 1 The illustrated scenario of the map drawing method is merely an example. The implementation environment of the map drawing method described in this application is for the purpose of more clearly illustrating the technical solutions of this application and does not constitute a limitation on the technical solutions provided in this application. Those skilled in the art will understand that, with the evolution of map drawing and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0064] The solutions provided in this application are specifically illustrated through the following embodiments. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0065] This embodiment will be described from the perspective of a map drawing device, which can be integrated into a computer device, which can be a server, and this application does not limit it.

[0066] Please see Figure 2 , Figure 2 This is a flowchart illustrating the map drawing method provided in an embodiment of this application. The map drawing method includes:

[0067] In step 101, the original map road network and historical trajectory points are obtained.

[0068] The original map road network can be a basic map road network pre-drawn based on road network data. This road network data abstracts real-world road conditions into point and line information and stores it for use in various map services, serving as the data foundation for map display and map services. This map road network can be a road network that abstracts real-world road conditions into point and line information. The original map road network can include at least one road segment. A road segment (Link) is the basic unit of a road in the map road network. A road may consist of multiple road segments, and each road segment can consist of two or more coordinate points. Each road segment can have a unique identifier (identity document, or id for short), namely the road segment identifier (Linkid).

[0069] The historical trajectory points can be trajectory points generated by an object moving within the area depicted by the original map network. These trajectory points can carry time and location information. The time information represents the time the trajectory point was generated, and the location information represents the object's position within the area corresponding to the original map road network. For example, it can be the object's coordinate information within the area corresponding to the original map road network, including coordinate information. The object can be a user, vehicle, or other object that can move on roads within the area corresponding to the original map network. There are various ways to obtain historical trajectory points. For example, user trajectory data can be obtained, and trajectory points can be extracted from the trajectory data to obtain the historical trajectory points of at least one object.

[0070] There are several ways to extract trajectory points from trajectory data; for example, please refer to... Figure 3 , Figure 3 This is a schematic flowchart of a map drawing method provided in an embodiment of this application. It can acquire original map road network and trajectory data, and perform trajectory preprocessing on the trajectory data to obtain historical trajectory points. There are various ways to preprocess the trajectory data. For example, invalid trajectories, drift trajectories, non-vehicle trajectories, and other trajectory noise can be filtered out and removed to select high-confidence trajectory points. Other preprocessing methods include noise reduction, supplementing with determined trajectory points, and trajectory smoothing. These methods allow for the extraction of historical trajectory points from the preprocessed trajectory data.

[0071] In step 102, candidate road segments matching the historical trajectory points are identified in the road segments based on the location information of the historical trajectory points.

[0072] The candidate road segment can be at least one road segment in the original map road network that matches the historical trajectory point, or it can be a road segment in the original map road network where the historical trajectory point may be located.

[0073] There are several ways to identify candidate road segments that match historical trajectory points based on their location information. For example, a tree structure corresponding to the original map road network can be constructed based on the road segments distributed in the original map road network. Based on the location information of the historical trajectory point, a search area corresponding to the historical trajectory point can be generated in the tree structure. Based on the search area, the tree structure can be traversed to obtain the candidate road segments corresponding to the historical trajectory point.

[0074] The tree diagram structure can be a data structure that represents the distribution relationship of road segments in the original map road network in the form of a tree diagram. This tree diagram, also known as a tree graph, can be a graphical representation of a data tree, organizing objects in a parent-child hierarchical structure. The search area can be the region in the tree diagram structure used to search for candidate road segments that match historical trajectory points within the tree diagram structure. The size of the search area can be set according to actual needs.

[0075] In one embodiment, the tree structure can be a spatial data index tree (RTree, or R-tree for short), and the search region can be a search rectangle in the R-tree. For example, please refer to... Figure 4 , Figure 4 This is a schematic diagram of a tree diagram structure for a map drawing method provided in this application embodiment. Assuming the left diagram represents a portion of the original map's road network, including road segments A, B, C, D, E, F, G, H, I, and J, a tree diagram structure corresponding to this original map's road network can be constructed using the spatial data index RTree. Figure 4 The right-hand diagram shows that the road network area can be divided into multiple rectangular regions (i.e., nodes in a tree diagram structure), namely P1, P2, P3, and P4. P1 includes road segments A, B, and C; P2 includes road segments D and E; P3 includes road segments F and G; and P4 includes road segments H, I, and J. Assuming that based on the location information of historical trajectory points, a search region S corresponding to each historical trajectory point can be generated in this tree diagram structure (i.e., the historical trajectory point is within the search region's range), when the search region S overlaps with nodes P3 and P4, the entries recorded in nodes P3 and P4 (i.e., the included road segments) can be searched, and the matching road segments found can be used as candidate road segments for historical trajectory points. Optionally, when node P3 or P4 is a non-leaf node in the tree diagram structure, the entries stored in P3 or P4 can be checked. For all these entries, a search operation can be performed on the root node of the subtree pointed to by each entry (i.e., the child node of P3 or P4), thereby determining candidate road segments for historical trajectory points based on the search results. When P3 or P4 is a leaf node in the tree diagram structure, all record entries pointed to by P3 or P4 can be checked directly, and then records that meet the conditions can be returned, with the corresponding fields determined as candidate fields.

[0076] Optionally, if the search area corresponding to a historical trajectory point does not overlap with the nodes in the tree structure corresponding to the original map road network, it indicates that no candidate road segment matching the historical trajectory point has been found.

[0077] In step 103, based on the distance between historical trajectory points and the connectivity of the original map road network, the transfer probability of historical trajectory points moving to candidate road segments is calculated, and based on the distance between historical trajectory points and candidate road segments, the emission probability of matching historical trajectory points to candidate road segments is calculated.

[0078] The distance between historical trajectory points can be the distance between the previous historical trajectory point and the current historical trajectory point according to their time sequence. To avoid the influence of latitude changes on the calculation results, this distance can be a spherical distance. The connectivity relationship can represent the distribution of road segments in the original map road network. The transition probability can be a numerical value representing the probability that a historical trajectory point will match a candidate road segment from the previous historical trajectory point. The emission probability can be a numerical value representing the probability that a historical trajectory point will match a candidate road segment.

[0079] There are several ways to calculate the transfer probability of a historical trajectory point to a candidate road segment based on the distance between historical trajectory points and the connectivity of the original map road network. For example, the trajectory path distance between the historical trajectory point and its associated trajectory points can be calculated based on the location information of the historical trajectory point and its associated trajectory points. Based on the connectivity of the original map road network, the planned path distance between the historical trajectory point and its associated trajectory points can be identified. Based on the trajectory path distance and the planned path distance, the transfer probability of the historical trajectory point to the candidate road segment based on the associated trajectory points can be calculated.

[0080] The associated trajectory point can be a trajectory point that is related to a historical trajectory point. For example, it can be the previous historical trajectory point of the current historical trajectory point, determined based on time information. The trajectory path distance can be the distance between the historical trajectory point and its corresponding associated trajectory point. To avoid the influence of latitude changes, this distance can be a spherical distance. The planned path distance can be the distance of the path from the associated trajectory point to the historical trajectory point, determined based on the connectivity of road segments in the original map road network.

[0081] There are several ways to calculate the trajectory path distance between a historical trajectory point and its associated trajectory points based on the location information of the historical trajectory point and its associated trajectory points. For example, the latitude and longitude coordinates of the historical trajectory point and its associated trajectory points can be determined based on the location information of the historical trajectory point and its associated trajectory points, so that the trajectory path distance between the historical trajectory point and its associated trajectory points can be calculated based on the Earth's radius.

[0082] There are several ways to identify the planned path distance between a historical trajectory point and an associated trajectory point based on the connectivity in the original map road network. For example, the candidate projection point of the historical trajectory point in the matched candidate road segment and the associated candidate projection point of the associated trajectory point in the corresponding associated candidate road segment can be determined in the original map road network. At the same time, the candidate planned path from the associated candidate projection point to the candidate projection point can be identified based on the connectivity in the original map road network, and the planned path distance from the associated trajectory point to the historical trajectory point can be calculated based on the candidate planned path.

[0083] Here, the candidate projection point can be the projection point of a historical trajectory point onto a matched candidate road segment. This projection point can be a point projected onto a straight line, i.e., a point determined by projecting a historical trajectory point onto a matched candidate road segment. The associated candidate road segment can be a candidate road segment matched by associated trajectory points, and the associated candidate projection point can be the projection point of the associated trajectory point onto a matched associated candidate road segment. The candidate planned path can be a path from the associated trajectory point to the historical trajectory point planned based on the candidate road segments matched by historical trajectory points and the associated candidate road segments matched by associated trajectory points, using the connectivity relationships in the original map's road network. For example, please refer to... Figure 5a , Figure 5a This is a schematic diagram of a map drawing method provided in this application embodiment. It is assumed that there are two corresponding historical trajectory points M and N in a certain area of ​​the original map road network. The historical trajectory point M is the previous trajectory point of the historical trajectory point N. That is, the historical trajectory point M is the associated trajectory point of the historical trajectory point N. According to the connectivity in the original map road network, the candidate planning path from the associated trajectory point M to the historical trajectory point N can be planned as the path from M to N along the dashed arrow, that is, the route from a to b to c to d.

[0084] After calculating the trajectory path distance and the planned path distance, the probability of a historical trajectory point moving to the candidate road segment based on associated trajectory points can be calculated using these distances. There are several ways to calculate this probability based on the trajectory path distance and the planned path distance. For example, a transfer probability calculation formula can be used, which can be expressed as follows:

[0085]

[0086] Wherein, p(d) t ) can be represented as a certain historical trajectory point d t Based on the previous trajectory point d t-1 Based on the matched associated candidate road segments, the current historical trajectory point d t The probability of matching a candidate road segment, i.e., the transition probability. Where d t It can be represented as

[0087]

[0088] Among them, ||z t -z t-1 || greatcircle z represents the distance along the trajectory path. t z represents a historical trajectory point. t-1 This represents the associated trajectory point corresponding to a historical trajectory point, i.e., the previous trajectory point. Indicates the distance of the planned path. This represents the projection point of the historical trajectory point onto the matched candidate road segment, i.e., the candidate projection point. This represents the projection point of the associated trajectory point in the matched candidate road segment, i.e., the associated candidate projection point.

[0089] The parameter β describes the difference between the planned path distance and the trajectory path distance; a larger β indicates a higher tolerance for the planned path. Optionally, a robust estimation can be used, expressed as...

[0090]

[0091] Among them, mediant t () represents the median function, which returns the median of a given value; ln() represents the logarithmic function.

[0092] There are several ways to calculate the emission probability of matching a historical trajectory point to a candidate road segment based on the distance between the historical trajectory point and the candidate road segment. For example, the trajectory projection point of the historical trajectory point in the candidate road segment can be identified in the original map road network, and the projection distance from the historical trajectory point to the trajectory projection point can be calculated. The system measurement error can be obtained, and the emission probability of matching the historical trajectory point to the candidate road segment can be calculated based on the system measurement error and the projection distance.

[0093] The trajectory projection point can be the projection point from the historical trajectory point to the candidate road segment, the projection distance can be the distance from the historical trajectory point to the trajectory projection point, and the system measurement error can be the standard deviation of the Global Positioning System (GPS) measurement. By estimating the distribution of GPS points and assuming that the distribution of GPS points is approximately Gaussian, the GPS measurement error can be effectively reduced.

[0094] There are several ways to calculate the transmission probability of matching the historical trajectory point to the candidate road segment based on the system measurement error and the projection distance. For example, a transmission probability calculation formula can be used to calculate the transmission probability of matching the historical trajectory point to the candidate road segment based on the system measurement error and the projection distance. This transmission probability calculation formula can be expressed as follows:

[0095]

[0096] Wherein, p(z) t |r i ) indicates that the historical trajectory point z t Matched candidate road segment r i The probability of emission, i.e., the probability of firing. Indicate z t Historical trajectory points projected onto candidate road segments r i The projection point, i.e., the trajectory projection point. Represents the historical trajectory point z t To the trajectory projection point The spherical distance, i.e., the projected distance, is used here to avoid the influence of latitude variations on the calculation of radiation probability. σ z This can be expressed as the standard deviation of GPS measurements, i.e., the system measurement error. Optionally, the median absolute deviation (MAD) can be used to estimate the system measurement error. For example, it can be expressed as...

[0097]

[0098] In the test data, the measurement error of the system can be approximated as 4.07 meters.

[0099] In one embodiment, the transmission probability and transfer probability of candidate road segments whose projected distance from the historical trajectory point to the trajectory projection point of the matched candidate road segment is greater than a preset distance threshold can be set to 0. This helps reduce the number of matched candidate road segments, thereby effectively reducing computational complexity. The preset distance threshold can be a pre-set critical value, for example, 200 meters. When the projected distance is greater than this critical value, the transmission probability and transfer probability of the corresponding candidate road segment can be set to 0, that is, the candidate road segment is determined as a road segment that does not match the historical trajectory point.

[0100] In step 104, target road segments that match historical trajectory points are selected from candidate road segments based on the transfer probability and the emission probability.

[0101] The target road segment can be a road segment that matches the historical trajectory point among the candidate road segments, that is, the road segment where the historical trajectory point is located in the original map road network.

[0102] There are several ways to select target road segments that match historical trajectory points from candidate road segments based on transfer probability and emission probability. For example, the probability weights corresponding to the transfer probability and emission probability can be obtained, and the transfer probability and emission probability can be weighted based on the probability weights respectively. The weighted transfer probability and emission probability can be fused together, and the target road segment can be selected from the candidate road segments based on the fusion result corresponding to the candidate road segment.

[0103] The probability weight can be the weight corresponding to the transition probability and the emission probability, which can be used to characterize the importance of the transition probability and the emission probability. The fusion result can be the result obtained by fusing the weighted transition probability and the emission probability.

[0104] There are several ways to fuse the weighted transition probabilities and emission probabilities. For example, the weighted transition probabilities and emission probabilities can be summed to determine the fusion result. For instance, assuming the probability weight corresponding to the transition probability (TP) is k and the probability weight corresponding to the emission probability (EP) is l, weighting the transition probability and emission probability based on these probability weights yields the weighted transition probability kTP and emission probability lEP. Summing the weighted transition probability and emission probability gives the fusion result kTP+lEP.

[0105] After fusing the weighted transition probability and emission probability, the target road segment can be selected from the candidate road segments based on the fusion result. There are several ways to select the target road segment from the candidate road segments based on the fusion result. For example, the candidate road segments corresponding to historical trajectory points can be sorted according to the probability values ​​of the fusion result, and the candidate road segment with the highest probability value can be determined as the target road segment.

[0106] Alternatively, the transfer probability and the launch probability can be directly summed, and the candidate road segment with the highest summation probability value can be determined as the target road segment.

[0107] Thus, after determining the target road segment corresponding to each historical trajectory point, we can obtain the optimal matching trajectory point set X. Each trajectory point element in set X can contain the transition probability TP and radiation probability EP of this historical trajectory point.

[0108] In step 105, based on the path information between historical trajectory points and the transfer probability from historical trajectory points to the target road segment, the missing road segments between historical trajectory points are determined.

[0109] The path information can represent the path distribution between historical trajectory points. The missing road segment can be a road segment that actually exists between historical trajectory points but is not present in the original map road network. The missing road segment can be a trajectory fragment composed of two or more historical trajectory points with a high launch probability but a low transfer probability. This trajectory fragment can be considered a missing road segment that is not present in the current original map road network, but allows the user to reach their destination "faster." For example, please continue to refer to... Figure 5a For a route from associated trajectory point M to historical trajectory point N, based on the connectivity of the original map road network, the planned route from associated trajectory point M to historical trajectory point N can be determined as M following the dashed arrow through a to b to c to d. However, based on the distribution of historical trajectory points determined by the actual movement trajectory data, it can be considered that there is a shorter route between associated trajectory point M and historical trajectory point N, without having to follow the longer planned route. Therefore, it can be assumed that there is a missing road segment between associated trajectory point M and historical trajectory point N in the original map road network. For example, it could be... Figure 5a The road segment corresponding to the solid arrow in the middle is the actual route formed by the historical trajectory points.

[0110] There are several ways to determine the missing road segments between historical trajectory points based on the path information between historical trajectory points and the transfer probability from the historical trajectory point to the target road segment. For example, the missing road segment probability corresponding to the historical trajectory point can be calculated based on the path information between the historical trajectory points and the transfer probability from the historical trajectory point to the target road segment. Based on the missing road segment probability, the missing road segments between the historical trajectory points can be identified.

[0111] The probability of a missing road segment can be defined as the probability that a missing road segment exists between the historical trajectory point and its associated trajectory points.

[0112] There are several ways to calculate the probability of missing road segments corresponding to a historical trajectory point based on the path information between the historical trajectory points and the transfer probability from the historical trajectory point to the target road segment. For example, based on the connectivity in the original map road network, the target planned path distance between the historical trajectory point and the associated trajectory point can be identified. Based on the location information of the historical trajectory point and the associated trajectory point, the target trajectory path distance between the historical trajectory point and the associated trajectory point can be calculated. The target transfer probability from the historical trajectory point to the target road segment based on the associated trajectory point can be obtained. Based on the target transfer probability, the target planned path distance, and the target trajectory path distance, the probability of missing road segments corresponding to the historical trajectory point can be calculated.

[0113] The target planned path distance can be the distance from the associated trajectory point to the historical trajectory point, determined based on the connectivity of road segments in the original map road network after the target road segment of the historical trajectory point has been determined. The target trajectory path distance can also be the spherical distance between the historical trajectory point and the associated trajectory point. The target transfer probability can be the transfer probability of a historical trajectory point moving to a target road segment matched by an associated trajectory point that has been matched with the associated target road segment. For example, please refer to... Figure 5b , Figure 5b This is a schematic diagram of path information for a map drawing method provided in this application embodiment, including historical trajectory point Z. i (TP i EP i The historical trajectory point Z is the historical trajectory point Z. i The previous trajectory point Z i-1 (TP i-1 EP i-1 ), where TP i EP represents the transition probability of this historical trajectory point. i TP represents the launch probability at this historical trajectory point. i-1 EP represents the transition probability of the associated trajectory point. i-1Given the emission probability of the associated trajectory point, the distance of the target's planned path can be the planned path D. route The distance of the target trajectory path can be determined by the trajectory path D. great circle The distance.

[0114] There are several ways to identify the target planned path distance between a historical trajectory point and its associated trajectory point based on the connectivity in the original map road network. For example, the projection point of the historical trajectory point in the target road segment and its associated projection point can be determined in the original map road network. Based on the connectivity in the original map road network, the planned path from the associated projection point to the projection point can be identified. Based on the planned path, the target planned path distance from the associated projection point to the projection point can be calculated.

[0115] Here, the associated projection point can be the projection point of the associated trajectory point corresponding to the historical trajectory point in the corresponding associated target road segment. The associated target road segment can be the target road segment matched by the associated trajectory point. The planned path can be a path planned from the associated projection point to the projection point based on the connectivity of road segments in the original map road network. For example, please refer to [link / reference]. Figure 5b The planned path is shown in the diagram.

[0116] Optionally, there are multiple ways to calculate the probability of missing road segments corresponding to a historical trajectory point based on the target transition probability, the target planned path distance, and the target trajectory path distance. For example, the road segment missing probability calculation formula can be used to calculate the probability of missing road segments corresponding to a historical trajectory point based on the target transition probability, the target planned path distance, and the target trajectory path distance. Alternatively, please refer to [further details]. Figure 5b The formula for calculating the probability of missing road sections can be expressed as follows:

[0117] P(z t ,z t-1 |r i )=|D route -D great circle | / D great circle ×ln(-1)(TP i -TP i-1 )×(1-TP i )×(1-TP i-1 )

[0118] Wherein, P(z) t ,z t-1 |r i () can represent the historical trajectory point z t Its corresponding associated trajectory point z t-1 There are missing road segments r iThe probability of a missing road segment, i.e., the probability of a missing road segment, is D. route This can be represented as the target planning path distance, where D... great circle This can be represented as the target trajectory path distance, TP i This can be represented as the historical trajectory point z. t The corresponding target transition probability, this TP i-1 It can be represented as the associated trajectory point z t-1 The corresponding target transition probability.

[0119] After calculating the road segment missing probability corresponding to a historical trajectory point based on the path information between the historical trajectory points and the transition probability from the historical trajectory point to the target road segment, the missing road segments between the historical trajectory points can be identified based on the road segment missing probability. There are several ways to identify missing road segments between historical trajectory points based on the road segment missing probability. For example, a missing probability threshold can be obtained, and the road segment missing probability can be compared with the missing probability threshold. When the road segment missing probability is greater than the missing probability threshold, the road segment corresponding to that missing probability is determined to be a missing road segment between the historical trajectory points.

[0120] The missing probability threshold can be a pre-defined probability cutoff value. When the missing probability of a road segment is greater than this cutoff value, it can be considered that there are missing road segments among the trajectory points corresponding to the missing probability of that road segment. When the missing probability of a road segment is not greater than this cutoff value, it can be considered that there are no missing road segments among the trajectory points corresponding to the missing probability of that road segment. The road segment corresponding to the missing probability of that road segment can refer to the road segment formed by the historical trajectory points corresponding to the determined probability of that road segment and the associated trajectory points corresponding to those historical trajectory points.

[0121] For example, please continue to refer to Figure 3 During trajectory matching, the system can calculate the transition probability and emission probability of each candidate road segment matched with historical trajectory points. Based on these probabilities, target road segments matching historical trajectory points can be selected from the candidate road segments. After determining the target road segment matching each historical trajectory point, the missing road segment probability corresponding to each historical trajectory point can be calculated to identify missing road segments. Optionally, after identifying missing road segments, a notification message can be sent to relevant personnel to verify the accuracy of the missing road segments, further increasing the accuracy of map drawing.

[0122] In step 106, the original map road network is drawn and updated based on the missing road segments to obtain the target map road network.

[0123] The target map road network can be an original map road network supplemented with missing road segments; that is, a map road network obtained by extracting missing road segments from the original map road network. For example, please refer to [link / reference]. Figure 3After updating the original map road network based on the discovered missing road segments, the drawn target map road network can be stored in the corresponding road network database for subsequent map applications. Therefore, the map drawing method provided in this application embodiment has good timeliness in identifying missing road segments. Furthermore, it can accurately identify short, dense connecting road segments, exhibiting high accuracy in missing road identification, thereby improving map drawing accuracy. At the product level, when users plan navigation routes, these short connecting roads can prevent users from taking detours, allowing them to reach their destination more quickly and improving the accuracy of map navigation.

[0124] As described above, this embodiment of the application obtains the original map road network and historical trajectory points, where the original map road network includes at least one road segment; based on the location information of the historical trajectory points, candidate road segments matching the historical trajectory points are identified within the road segments; based on the distance between historical trajectory points and the connectivity of the original map road network, the transfer probability of historical trajectory points moving to candidate road segments is calculated, and based on the distance between historical trajectory points and candidate road segments, the emission probability of matching historical trajectory points to candidate road segments is calculated; based on the transfer probability and emission probability, target road segments matching historical trajectory points are selected from the candidate road segments; based on the path information between historical trajectory points and the transfer probability from historical trajectory points to target road segments, missing road segments existing between historical trajectory points are determined; and the original map road network is drawn and updated based on the missing road segments to obtain the target map road network. In this way, by calculating the transition probability and emission probability corresponding to historical trajectory points, the target road segment matching the historical trajectory points is determined in the original map road network. Based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments, the missing road segments between historical trajectory points are determined. Based on the determined missing road segments, the original map road network is drawn and updated, supplementing the missing road segments in the original map road network, improving the accuracy of map drawing, and thus improving map drawing efficiency.

[0125] Based on the method described in the above embodiments, the following examples will provide further detailed explanations.

[0126] In this embodiment, the map drawing device will be specifically integrated into a computer device as an example for explanation. The map drawing method will be specifically described using a server as the executing entity.

[0127] For a better description of the embodiments of this application, please refer to Figure 6 , Figure 6 Another flowchart illustrating the map drawing method provided in this application embodiment. The specific process is as follows:

[0128] In step 201, the server obtains the original map road network and historical trajectory points, and constructs a tree diagram structure corresponding to the original map road network based on the road segments distributed in the original map road network.

[0129] There are several ways for a server to obtain historical trajectory points. For example, a server can obtain a user's trajectory data, extract trajectory points from the trajectory data, and thus obtain the historical trajectory points of at least one object.

[0130] There are several ways for the server to extract trajectory points from the trajectory data. For example, please refer to [reference needed]. Figure 3 The server can acquire raw map road network and trajectory data, and perform trajectory preprocessing to obtain historical trajectory points. The server can perform preprocessing on the trajectory data in various ways. For example, it can filter out and remove trajectory noise such as invalid trajectories, drift trajectories, and non-vehicle trajectories, thereby selecting high-confidence trajectory points. It can also perform preprocessing methods such as noise reduction, supplementing with confirmed trajectory points, and trajectory smoothing, thus extracting historical trajectory points from the preprocessed trajectory data.

[0131] After obtaining the original map road network and historical trajectory points, the server can construct a tree structure corresponding to the original map road network based on the road segments distributed in the original map road network. There are several ways for the server to construct the tree structure based on the road segments distributed in the original map road network. For example, RTree can be used to construct the tree structure corresponding to the original map road network based on the road segments distributed in the original map road network.

[0132] In step 202, the server generates a search area corresponding to the historical trajectory point in the tree structure based on the location information of the historical trajectory point, and traverses the tree structure according to the search area to obtain the candidate road segment corresponding to the historical trajectory point.

[0133] For example, please refer to Figure 4 Assuming the left image represents a portion of the original map's road network, including road segments A, B, C, D, E, F, G, H, I, and J, a tree structure corresponding to this original map's road network can be constructed using the spatial data index RTree, as follows: Figure 4The right-hand diagram shows that the road network area can be divided into multiple rectangular regions (i.e., nodes in a tree diagram structure), namely P1, P2, P3, and P4. P1 includes road segments A, B, and C; P2 includes road segments D and E; P3 includes road segments F and G; and P4 includes road segments H, I, and J. Assuming that based on the location information of historical trajectory points, a search region S corresponding to each historical trajectory point can be generated in this tree diagram structure (i.e., the historical trajectory point is within the search region), and search region S overlaps with nodes P3 and P4, therefore, the entries recorded in nodes P3 and P4 (i.e., the road segments they contain) can be searched, and the matching road segments found can be used as candidate road segments for historical trajectory points. Optionally, when nodes P3 or P4 are non-leaf nodes in the tree diagram structure, the entries stored in P3 or P4 can be checked. For all these entries, the Search operation can be applied to the root node of the subtree pointed to by each entry, thereby determining the candidate road segments for historical trajectory points based on the search results. When P3 or P4 is a leaf node in the tree diagram structure, all record entries pointed to by P3 or P4 can be directly checked, and then records that meet the conditions can be returned and the corresponding fields can be identified as candidate fields.

[0134] Optionally, if the search area corresponding to a historical trajectory point does not overlap with the nodes in the tree structure corresponding to the original map road network, it indicates that no candidate road segment matching the historical trajectory point has been found.

[0135] In step 203, the server calculates the trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point, and identifies the planned path distance between the historical trajectory point and the associated trajectory point based on the connectivity in the original map road network.

[0136] There are several ways for the server to calculate the trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point. For example, the server can determine the latitude and longitude coordinates of the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point, and then calculate the trajectory path distance between the historical trajectory point and the associated trajectory point based on the Earth's radius.

[0137] There are several ways for the server to identify the planned path distance between the historical trajectory point and the associated trajectory point based on the connectivity in the original map road network. For example, the server can determine the candidate projection point of the historical trajectory point in the matching candidate road segment and the associated candidate projection point of the associated trajectory point in the corresponding associated candidate road segment in the original map road network. At the same time, based on the connectivity in the original map road network, the server can identify the candidate planned path from the associated candidate projection point to the candidate projection point, and calculate the planned path distance from the associated trajectory point to the historical trajectory point based on the candidate planned path.

[0138] In step 204, the server calculates the transfer probability of the historical trajectory point to the candidate road segment based on the trajectory path distance and the planned path distance.

[0139] There are several ways for the server to calculate the transfer probability of a historical trajectory point moving to the candidate road segment based on associated trajectory points, according to the distance of the trajectory path and the distance of the planned path. For example, the server can use a transfer probability calculation formula to calculate the transfer probability of a historical trajectory point moving to the candidate road segment based on associated trajectory points. This transfer probability calculation formula can be expressed as follows:

[0140]

[0141] Wherein, p(d) t ) can be represented as a certain historical trajectory point d t Based on the previous trajectory point d t-1 Based on the matched associated candidate road segments, the current historical trajectory point d t The probability of matching a candidate road segment, i.e., the transition probability. Where d t It can be represented as

[0142]

[0143] Among them, ||z t -z t-1 || greatcircle z represents the distance along the trajectory path. t z represents a historical trajectory point. t-1 This represents the associated trajectory point corresponding to a historical trajectory point, i.e., the previous trajectory point. Indicates the distance of the planned path. This represents the projection point of the historical trajectory point onto the matched candidate road segment, i.e., the candidate projection point. This represents the projection point of the associated trajectory point in the matched candidate road segment, i.e., the associated candidate projection point.

[0144] The parameter β describes the difference between the planned path distance and the trajectory path distance; a larger β indicates a higher tolerance for the planned path. Optionally, a robust estimation can be used, expressed as...

[0145]

[0146] Among them, mediant t () represents the median function, which returns the median of a given value; ln() represents the logarithmic function.

[0147] In step 205, the server identifies the trajectory projection point of the historical trajectory point in the candidate road segment in the original map road network, calculates the projection distance from the historical trajectory point to the trajectory projection point, obtains the system measurement error, and calculates the emission probability of matching the historical trajectory point to the candidate road segment based on the system measurement error and the projection distance.

[0148] There are several ways for the server to calculate the transmission probability of matching a historical trajectory point to a candidate road segment based on the system measurement error and the projection distance. For example, the server can use a transmission probability calculation formula to calculate the transmission probability of matching a historical trajectory point to a candidate road segment based on the system measurement error and the projection distance. This transmission probability calculation formula can be expressed as follows:

[0149]

[0150] Wherein, p(z) t |r i ) indicates that the historical trajectory point z t Matched candidate road segment r i The probability of emission, i.e., the probability of firing. Indicate z t Historical trajectory points projected onto candidate road segments r i The projection point, i.e., the trajectory projection point. Represents the historical trajectory point z t To the trajectory projection point The spherical distance, i.e., the projected distance, is used here to avoid the influence of latitude variations on the calculation of radiation probability. σ z This can be expressed as the standard deviation of GPS measurements, i.e., the system measurement error. Optionally, the median absolute deviation (MAD) can be used to estimate the system measurement error. For example, it can be expressed as...

[0151]

[0152] In the test data, the measurement error of the system can be approximated as 4.07 meters.

[0153] In one embodiment, the server can set the transmission probability and transfer probability of candidate road segments whose projected distance from historical trajectory points to the trajectory projection points of matched candidate road segments is greater than a preset distance threshold to 0. This helps reduce the number of matched candidate road segments, thereby effectively reducing computational complexity. The preset distance threshold can be a pre-set critical value, for example, 200 meters. When the projected distance is greater than this critical value, the transmission probability and transfer probability of the corresponding candidate road segment can be set to 0, that is, the candidate road segment is determined as a road segment that does not match the historical trajectory points.

[0154] In step 206, the server selects the target road segment that matches the historical trajectory point from the candidate road segments based on the transfer probability and the transmission probability.

[0155] There are several ways for the server to select target road segments that match historical trajectory points from candidate road segments based on the transfer probability and the emission probability. For example, the server can obtain the probability weights corresponding to the transfer probability and the emission probability, weight the transfer probability and the emission probability respectively based on the probability weights, fuse the weighted transfer probability and the emission probability, and select the target road segment from the candidate road segments according to the fusion result corresponding to the candidate road segment.

[0156] There are several ways for the server to fuse the weighted transition probabilities and emission probabilities. For example, the server can accumulate the weighted transition probabilities and emission probabilities to determine the fusion result. For instance, assuming the probability weight corresponding to the transition probability (TP) is k and the probability weight corresponding to the emission probability (EP) is l, then by weighting the transition probability and the emission probability respectively based on these probability weights, we can obtain the weighted transition probability kTP and the emission probability lEP. Accumulating the weighted transition probability and the emission probability yields the fusion result kTP+lEP.

[0157] After fusing the weighted transition probabilities and transmission probabilities, the server can select the target road segment from the candidate road segments based on the fusion result. There are several ways the server can select the target road segment from the candidate road segments based on the fusion result. For example, it can sort the candidate road segments corresponding to historical trajectory points according to the probability values ​​of the fusion results and determine the candidate road segment with the highest probability value as the target road segment.

[0158] Optionally, the server can also directly sum the transfer probability and the launch probability, and determine the candidate road segment with the highest summation probability as the target road segment, etc.

[0159] In step 207, the server determines the projection point of the historical trajectory point in the target road segment and the associated projection point corresponding to the historical trajectory point in the original map road network. Based on the connectivity in the original map road network, the server identifies the planned path from the associated projection point to the projection point. Based on the planned path, the server calculates the target planned path distance from the associated projection point to the projection point.

[0160] The associated projection point can be the projection point of the associated trajectory point corresponding to the historical trajectory point in the corresponding associated target road segment. The associated target road segment can be the target road segment matched by the associated trajectory point. The planned path can be the path from the associated projection point to the projection point planned based on the connectivity of road segments in the original map road network.

[0161] In step 208, the server calculates the target trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point, obtains the target transfer probability of the historical trajectory point to the target road segment based on the associated trajectory point, and calculates the road segment missing probability corresponding to the historical trajectory point based on the target transfer probability, the target planned path distance and the target trajectory path distance.

[0162] Optionally, the server can calculate the probability of missing road segments corresponding to a historical trajectory point based on the target transition probability, the distance to the target's planned path, and the distance to the target's trajectory path in several ways. For example, the server can use a road segment missing probability calculation formula based on the target transition probability, the distance to the target's planned path, and the distance to the target's trajectory path to calculate the probability of missing road segments corresponding to a historical trajectory point. For further details, please refer to [link / reference]. Figure 5b The formula for calculating the probability of missing road sections can be expressed as follows:

[0163] P(z t ,z t-1 |r i )=|D route -D great circle | / D grea t circle ×ln(-1)(TP i -TP i-1 )×(1-TP i )×(1-TP i-1 )

[0164] Wherein, P(z) t ,z t-1 |r i () can represent the historical trajectory point z t Its corresponding associated trajectory point z t-1 There are missing road segments r i The probability of a missing road segment, i.e., the probability of a missing road segment, is D.route This can be represented as the target planning path distance, where D... great circle This can be represented as the target trajectory path distance, TP i This can be represented as the historical trajectory point z. t The corresponding target transition probability, this TP i-1 It can be represented as the associated trajectory point z t-1 The corresponding target transition probability.

[0165] In step 209, the server identifies missing road segments between historical trajectory points based on the missing probability of the road segment, and updates the original map road network based on the missing road segments to obtain the target map road network.

[0166] There are several ways for the server to identify missing road segments among historical trajectory points based on the missing probability of the road segment. For example, the server can obtain a missing probability threshold and compare the missing probability of the road segment with the missing probability threshold. When the missing probability of the road segment is greater than the missing probability threshold, the road segment corresponding to the missing probability of the road segment is determined to be a missing road segment among historical trajectory points.

[0167] For example, please continue to refer to Figure 3 The server can calculate the transition probability and emission probability of each candidate road segment matched by historical trajectory points during the trajectory matching process. Based on these probabilities, it can then filter out target road segments that match historical trajectory points from among the candidate road segments. After determining the target road segment matched by each historical trajectory point, the server can calculate the road segment missing probability corresponding to each historical trajectory point to identify missing road segments. Optionally, after identifying missing road segments, the server can send a notification to relevant personnel to verify the accuracy of the missing road segments, further increasing the accuracy of map drawing. After updating the original map road network based on the identified missing road segments, the drawn target map road network can be stored in the corresponding road network database for subsequent map applications. Therefore, the map drawing method provided in this application embodiment has good timeliness in identifying missing road segments. Furthermore, it can accurately identify short, densely connected road segments, exhibiting high accuracy in identifying missing roads, thereby improving the accuracy of map drawing. At the product level, when users plan their navigation routes, these short connecting roads can prevent the planned routes from being "detours," allowing users to reach their destinations more quickly and improving the accuracy of map navigation.

[0168] As described above, this embodiment of the application obtains the original map road network and historical trajectory points through a server. Based on the road segments distributed in the original map road network, a tree diagram structure corresponding to the original map road network is constructed. Based on the location information of the historical trajectory points, the server generates a search area corresponding to the historical trajectory points in the tree diagram structure. Based on the search area, the tree diagram structure is traversed to obtain candidate road segments corresponding to the historical trajectory points. Based on the location information of the historical trajectory points and their corresponding associated trajectory points, the server calculates the trajectory path distance between the historical trajectory points and their associated trajectory points. Based on the connectivity in the original map road network, the server identifies the planned path distance between the historical trajectory points and their associated trajectory points. Based on the trajectory path distance and the planned path distance, the server calculates the transfer probability of the historical trajectory points moving to the candidate road segments based on the associated trajectory points. The server identifies the trajectory projection point of the historical trajectory point in the candidate road segment within the original map road network, calculates the projection distance from the historical trajectory point to the trajectory projection point, obtains the system measurement error, and based on the system measurement error and the projection distance... The server calculates the emission probability of matching the historical trajectory point to the candidate road segment; based on the transition probability and emission probability, the server filters out the target road segment that matches the historical trajectory point from the candidate road segments; the server determines the projection point of the historical trajectory point in the target road segment and the associated projection point of the historical trajectory point in the original map road network, and identifies the planned path from the associated projection point to the projection point based on the connectivity in the original map road network, and calculates the target planned path distance from the associated projection point to the projection point based on the planned path; based on the location information of the historical trajectory point and the associated trajectory point, the server calculates the target trajectory path distance between the historical trajectory point and the associated trajectory point, obtains the target transition probability of the historical trajectory point to the target road segment based on the associated trajectory point, and calculates the road segment missing probability corresponding to the historical trajectory point based on the target transition probability, the target planned path distance, and the target trajectory path distance; based on the road segment missing probability, the server identifies the missing road segments between the historical trajectory points, and updates the original map road network based on the missing road segments to obtain the target map road network. In this way, by calculating the transition probability and emission probability corresponding to historical trajectory points, the target road segment matching the historical trajectory points is determined in the original map road network. Based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments, the missing road segment probability corresponding to the historical trajectory points is calculated. Based on the missing road segment probability, the missing road segments between historical trajectory points are determined. Then, the original map road network is drawn and updated based on the determined missing road segments, which fills in the missing road segments in the original map road network, improves the accuracy of map drawing, and thus improves the efficiency of map drawing.

[0169] To better implement the above methods, embodiments of the present invention also provide a map drawing device, which can be integrated into a computer device, which can be a server.

[0170] For example, such as Figure 7 The diagram shown is a schematic representation of the map drawing device provided in this application embodiment. The map drawing device may include an acquisition unit 301, an identification unit 302, a calculation unit 303, a filtering unit 304, a determination unit 305, and a drawing unit 306, as follows:

[0171] The acquisition unit 301 is used to acquire the original map road network and historical trajectory points, wherein the original map road network includes at least one road segment.

[0172] The identification unit 302 is used to identify candidate road segments matching the historical trajectory point in the road segment based on the location information of the historical trajectory point.

[0173] The calculation unit 303 is used to calculate the transfer probability of the historical trajectory point to the candidate road segment based on the distance between the historical trajectory points and the connectivity of the original map road network, and to calculate the emission probability of matching the historical trajectory point to the candidate road segment based on the distance between the historical trajectory point and the candidate road segment.

[0174] The filtering unit 304 is used to filter out the target road segment that matches the historical trajectory point from the candidate road segments based on the transfer probability and the emission probability.

[0175] The determining unit 305 is used to determine the missing road segments between the historical trajectory points based on the path information between the historical trajectory points and the transition probability from the historical trajectory points to the target road segment.

[0176] The drawing unit 306 is used to draw and update the original map road network based on the missing road segment to obtain the target map road network.

[0177] In one embodiment, the determining unit 305 includes:

[0178] The road segment missing probability calculation subunit is used to calculate the road segment missing probability corresponding to the historical trajectory point based on the path information between the historical trajectory points and the transfer probability from the historical trajectory point to the target road segment.

[0179] The missing road segment identification subunit is used to identify missing road segments that exist between historical trajectory points based on the probability of the missing road segment.

[0180] In one embodiment, the road segment missing probability calculation subunit includes:

[0181] The target planning path distance identification module is used to identify the target planning path distance between the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point based on the connectivity in the original map road network.

[0182] The target trajectory path distance calculation module is used to calculate the target trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point.

[0183] The road segment missing probability calculation module is used to obtain the target transfer probability of the historical trajectory point to the target road segment based on the associated trajectory point, and to calculate the road segment missing probability corresponding to the historical trajectory point based on the target transfer probability, the target planned path distance and the direct path distance.

[0184] In one embodiment, the target planning path distance identification module includes:

[0185] The determination submodule is used to determine the projection point of the historical trajectory point in the target road segment in the original map road network, as well as the associated projection point corresponding to the historical trajectory point. The associated projection point is the projection point of the associated trajectory point of the historical trajectory point in the corresponding associated target road segment.

[0186] The identification submodule is used to identify the planned path from the associated projection point to the projection point based on the connectivity in the original map road network;

[0187] The calculation submodule is used to calculate the target planned path distance from the associated projection point to the projection point based on the planned path.

[0188] In one embodiment, the computing unit 303 includes:

[0189] The trajectory path distance calculation subunit is used to calculate the trajectory path distance between the historical trajectory point and the associated trajectory point based on the location information of the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point.

[0190] The planned path distance identification subunit is used to identify the planned path distance between the historical trajectory point and the associated trajectory point based on the connectivity in the original map road network;

[0191] The transition probability calculation subunit is used to calculate the transition probability of a historical trajectory point moving to the candidate road segment based on the trajectory path distance and the planned path distance.

[0192] In one embodiment, the computing unit 303 includes:

[0193] The projection distance calculation subunit is used to identify the trajectory projection point of the historical trajectory point in the candidate road segment in the original map road network, and to calculate the projection distance from the historical trajectory point to the trajectory projection point.

[0194] The emission probability calculation subunit is used to obtain the system measurement error and, based on the system measurement error and the projection distance, calculate the emission probability of matching the historical trajectory point to the candidate road segment.

[0195] In one embodiment, the identification unit 302 includes:

[0196] Construct sub-units to build a tree structure corresponding to the original map road network based on the road segments distributed in the original map road network;

[0197] A sub-unit is generated to generate the search area corresponding to the historical trajectory point in the tree structure based on the location information of the historical trajectory point.

[0198] The sub-unit traversal is used to traverse the tree structure based on the search area to obtain the candidate road segments corresponding to the historical trajectory points.

[0199] In one embodiment, the screening unit 304 includes:

[0200] The weight acquisition subunit is used to acquire the transition probability and the probability weight corresponding to the emission probability.

[0201] The weighted subunit is used to weight the transition probability and the emission probability based on the probability weights respectively;

[0202] The filtering subunit is used to fuse the weighted transition probability and emission probability, and select the target road segment from the candidate road segment based on the fusion result corresponding to the candidate road segment.

[0203] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0204] As can be seen from the above, in this embodiment of the application, the acquisition unit 301 acquires the original map road network and historical trajectory points, the original map road network including at least one road segment; the identification unit 302 identifies candidate road segments matching the historical trajectory points in the road segments based on the location information of the historical trajectory points; the calculation unit 303 calculates the transfer probability of historical trajectory points moving to candidate road segments based on the distance between historical trajectory points and the connectivity of the original map road network, and calculates the emission probability of matching historical trajectory points to candidate road segments based on the distance between historical trajectory points and candidate road segments; the filtering unit 304 filters out target road segments matching historical trajectory points in the candidate road segments based on the transfer probability and emission probability; the determination unit 305 determines the missing road segments between historical trajectory points based on the path information between historical trajectory points and the transfer probability from historical trajectory points to target road segments; and the drawing unit 306 draws and updates the original map road network based on the missing road segments to obtain the target map road network. In this way, by calculating the transition probability and emission probability corresponding to historical trajectory points, the target road segment matching the historical trajectory points is determined in the original map road network. Based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments, the missing road segments between historical trajectory points are determined. Based on the determined missing road segments, the original map road network is drawn and updated, supplementing the missing road segments in the original map road network, improving the accuracy of map drawing, and thus improving map drawing efficiency.

[0205] This application also provides a computer device, such as... Figure 8 As shown, it illustrates a structural diagram of a computer device involved in an embodiment of this application. This computer device may be a server, specifically:

[0206] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 8 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0207] Processor 401 is the control center of the computer device, connecting various parts of the computer device through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in memory 402, and by calling data stored in memory 402. Optionally, processor 401 may include one or more processing cores; preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 401.

[0208] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and map drawing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0209] The computer device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0210] The computer device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0211] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0212] The process involves: acquiring the original map road network and historical trajectory points, with the original map road network including at least one road segment; identifying candidate road segments that match the historical trajectory points based on their location information; calculating the transition probability of historical trajectory points moving to candidate road segments based on the distance between historical trajectory points and the connectivity of the original map road network, and calculating the emission probability of matching historical trajectory points to candidate road segments based on the distance between historical trajectory points and candidate road segments; selecting target road segments that match historical trajectory points from the candidate road segments based on the transition and emission probabilities; identifying missing road segments between historical trajectory points based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments; and updating the original map road network based on the missing road segments to obtain the target map road network.

[0213] The specific implementation of each of the above operations can be found in the preceding embodiments, and will not be repeated here. It should be noted that the computer device provided in this application embodiment and the map drawing method in the above embodiments belong to the same concept, and its specific implementation process can be found in the above method embodiments, and will not be repeated here.

[0214] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0215] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the map drawing methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0216] The process involves: acquiring the original map road network and historical trajectory points, with the original map road network including at least one road segment; identifying candidate road segments that match the historical trajectory points based on their location information; calculating the transition probability of historical trajectory points moving to candidate road segments based on the distance between historical trajectory points and the connectivity of the original map road network, and calculating the emission probability of matching historical trajectory points to candidate road segments based on the distance between historical trajectory points and candidate road segments; selecting target road segments that match historical trajectory points from the candidate road segments based on the transition and emission probabilities; identifying missing road segments between historical trajectory points based on the path information between historical trajectory points and the transition probability from historical trajectory points to target road segments; and updating the original map road network based on the missing road segments to obtain the target map road network.

[0217] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0218] Since the instructions stored in the computer-readable storage medium can execute the steps of any of the map drawing methods provided in the embodiments of this application, the beneficial effects that any of the map drawing methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0219] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the above embodiments.

[0220] The foregoing has provided a detailed description of a map drawing method, apparatus, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A map drawing method, characterized in that, include: Obtain the original map road network and historical trajectory points, wherein the original map road network includes at least one road segment; Based on the location information of the historical trajectory points, candidate road segments matching the historical trajectory points are identified in the road segment; Based on the distance between the historical trajectory points and the connectivity of the original map road network, the transfer probability of the historical trajectory point moving to the candidate road segment is calculated, and based on the distance between the historical trajectory point and the candidate road segment, the emission probability of matching the historical trajectory point to the candidate road segment is calculated. Based on the transfer probability and the emission probability, target road segments that match the historical trajectory points are selected from the candidate road segments; Based on the connectivity in the original map road network, the target planned path distance between the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point is identified; Based on the location information of the historical trajectory points and associated trajectory points, the target trajectory path distance between the historical trajectory points and associated trajectory points is calculated; Obtain the target transfer probability from the historical trajectory point to the target road segment based on the associated trajectory point, and calculate the road segment missing probability corresponding to the historical trajectory point based on the target transfer probability, the target planned path distance, and the target trajectory path distance; Based on the road segment missing probability, the missing road segments that exist between the historical trajectory points are identified; The original map road network is drawn and updated based on the missing road segments to obtain the target map road network.

2. The map drawing method as described in claim 1, characterized in that, The step of identifying the target planned path distance between the historical trajectory points and their corresponding associated trajectory points based on the connectivity relationships in the original map road network includes: In the original map road network, the projection point of the historical trajectory point in the target road segment is determined, as well as the associated projection point corresponding to the historical trajectory point. The associated projection point is the projection point of the associated trajectory point of the historical trajectory point in the corresponding associated target road segment. Based on the connectivity in the original map road network, a planned path from the associated projection point to the projection point is identified; Based on the planned path, calculate the target planned path distance from the associated projection point to the projection point.

3. The map drawing method as described in claim 1, characterized in that, The calculation of the transfer probability of a historical trajectory point moving to the candidate road segment based on the distance between the historical trajectory points and the connectivity of the original map road network includes: Based on the location information of the historical trajectory points and the associated trajectory points corresponding to the historical trajectory points, calculate the trajectory path distance between the historical trajectory points and the associated trajectory points; Based on the connectivity in the original map road network, the planned path distance between the historical trajectory points and related trajectory points is identified; Based on the trajectory path distance and the planned path distance, the transfer probability of the historical trajectory point to the candidate road segment based on the associated trajectory point is calculated.

4. The map drawing method as described in claim 1, characterized in that, The step of calculating the emission probability of matching the historical trajectory point to the candidate road segment based on the distance between the historical trajectory point and the candidate road segment includes: In the original map road network, the trajectory projection points of the historical trajectory points in the candidate road segments are identified, and the projection distance from the historical trajectory points to the trajectory projection points is calculated; The system measurement error is obtained, and based on the system measurement error and the projection distance, the emission probability of matching the historical trajectory point to the candidate road segment is calculated.

5. The map drawing method as described in claim 1, characterized in that, The step of identifying candidate road segments matching the historical trajectory points in the road segment based on the location information of the historical trajectory points includes: Based on the road segments distributed in the original map road network, construct a tree diagram structure corresponding to the original map road network; Based on the location information of the historical trajectory points, a search area corresponding to the historical trajectory points is generated in the tree diagram structure; Based on the search area, the tree structure is traversed to obtain the candidate road segments corresponding to the historical trajectory points.

6. The map drawing method as described in claim 1, characterized in that, The step of selecting target road segments that match the historical trajectory points from the candidate road segments based on the transfer probability and the emission probability includes: Obtain the transition probability and the probability weight corresponding to the emission probability; The transition probability and the emission probability are weighted based on the probability weights, respectively. The weighted transition probability and emission probability are fused together, and the target road segment is selected from the candidate road segments based on the fusion result corresponding to the candidate road segments.

7. A map drawing device, characterized in that, include: The acquisition unit is used to acquire the original map road network and historical trajectory points, wherein the original map road network includes at least one road segment; The identification unit is used to identify candidate road segments matching the historical trajectory points in the road segment based on the location information of the historical trajectory points; The calculation unit is used to calculate the transfer probability of the historical trajectory point to the candidate road segment based on the distance between the historical trajectory points and the connectivity of the original map road network, and to calculate the emission probability of matching the historical trajectory point to the candidate road segment based on the distance between the historical trajectory point and the candidate road segment. A filtering unit is used to filter out target road segments that match the historical trajectory points from the candidate road segments based on the transfer probability and the emission probability. The determining unit is used to identify the target planned path distance between the historical trajectory point and the associated trajectory point corresponding to the historical trajectory point based on the connectivity relationship in the original map road network; and to calculate the target trajectory path distance between the historical trajectory point and the associated trajectory point according to the location information of the historical trajectory point and the associated trajectory point. Obtain the target transfer probability from the historical trajectory point to the target road segment based on the associated trajectory point, and calculate the road segment missing probability corresponding to the historical trajectory point based on the target transfer probability, the target planned path distance, and the target trajectory path distance; Based on the road segment missing probability, the missing road segments that exist between the historical trajectory points are identified; The drawing unit is used to draw and update the original map road network based on the missing road segments to obtain the target map road network.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the map drawing method according to any one of claims 1 to 6.

9. A computer device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the map drawing method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the steps of the map drawing method according to any one of claims 1 to 6.

Images