Method, apparatus, storage medium and electronic device for determining missing roads on a map

Abstract

The present disclosure relates to the technical field of electronic maps, and specifically relates to a method for determining missing roads on a map, a device for determining missing roads on a map, a computer-readable storage medium, and an electronic device. In an exemplary embodiment of the present disclosure, the method for determining missing roads on a map includes: determining a cluster of trajectory points corresponding to a suspected missing road, which is composed of a plurality of movement trajectory points; obtaining the movement position information and movement direction information of each of the movement trajectory points in the cluster of trajectory points; and determining the road confidence level that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information. This method can not only save a large amount of labor costs, but also greatly improve the efficiency and accuracy of determining missing roads on the map, so as to be able to automatically and efficiently and accurately complete the road network of the electronic map.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electronic maps, and in particular, to a method for determining missing roads on a map, a device for determining missing roads on a map, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the development of society and economy, as well as the progress of computer technology and network technology, electronic maps have become an essential tool in people's daily lives. Whether for daily travel or business trips and tourism, navigation and positioning technologies based on electronic maps can bring great convenience to people.

[0003] However, with the continuous acceleration of infrastructure construction, the regional landscape is also changing rapidly. This has led to the need for continuous updating of the road network data in electronic maps in order to provide users with real and effective road information. Especially for newly built roads, as well as roads under maintenance or construction that are newly opened, how to accurately and efficiently complete the missing roads in electronic maps in a timely manner is an urgent problem to be solved at present.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a method for determining missing roads on a map, a device for determining missing roads on a map, a computer-readable storage medium, and an electronic device, so as to at least to a certain extent overcome the technical problems such as low efficiency and poor accuracy in completing missing roads in related technologies.

[0006] According to one aspect of the present disclosure, there is provided a method for determining missing roads on a map, the method comprising:

[0007] Determining a cluster of trajectory points corresponding to a suspected missing road, which is composed of a plurality of movement trajectory points;

[0008] Obtaining the movement position information and movement direction information of each of the movement trajectory points in the cluster of trajectory points;

[0009] Determining the road confidence level that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information.

[0010] In some exemplary embodiments of the present disclosure, based on the above technical solution, determining the road confidence level that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information includes:

[0011] Determine the dispersion degree of the trajectory point clusters for representing the position dispersion degree between each of the motion trajectory points according to the motion position information;

[0012] Determine the disorder degree of the trajectory point clusters for representing the direction disorder degree of each of the motion trajectory points according to the motion direction information;

[0013] Determine the road confidence level that the suspected missing road is a map missing road according to the dispersion degree and the disorder degree.

[0014] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining the dispersion degree of the trajectory point clusters for representing the position dispersion degree between each of the motion trajectory points according to the motion position information includes:

[0015] Determine the position distance between each of the motion trajectory points and each of the other motion trajectory points according to the motion position information of each of the motion trajectory points;

[0016] Determine the trajectory point dispersion degree of each of the motion trajectory points in the trajectory point clusters according to the position distance;

[0017] Determine the dispersion degree of the trajectory point clusters for representing the position dispersion degree between each of the motion trajectory points according to the trajectory point dispersion degree of the motion trajectory points.

[0018] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining the disorder degree of the trajectory point clusters for representing the direction disorder degree of each of the motion trajectory points according to the motion direction information includes:

[0019] Determine a plurality of direction intervals corresponding to different direction ranges;

[0020] Divide each of the motion trajectory points in the trajectory point clusters into the direction intervals according to the motion direction information;

[0021] Determine the quantity ratio between the motion trajectory points in each direction interval and all the motion trajectory points in the trajectory point clusters according to the division result of the direction intervals;

[0022] Determine the disorder degree of the trajectory point clusters for representing the direction disorder degree of each of the motion trajectory points according to the quantity ratio.

[0023] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining a plurality of direction intervals corresponding to different direction ranges includes:

[0024] Determine the direction range covering all motion directions on the map plane;

[0025] Divide the direction range into a plurality of direction intervals with the same range size.

[0026] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining the road confidence that the suspected missing road is a map missing road according to the dispersion degree and the disorder degree includes:

[0027] Perform normalization processing on the dispersion degree and the disorder degree respectively to obtain a normalized dispersion degree and a normalized disorder degree;

[0028] Determine the road confidence that the suspected missing road is a map missing road according to the normalized dispersion degree and the normalized disorder degree.

[0029] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining a trajectory point cluster corresponding to a suspected missing road composed of a plurality of motion trajectory points includes:

[0030] Obtain the motion trajectory information of the target object, and determine the motion trajectory points of the target object on the map according to the motion trajectory information;

[0031] Screen the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain target trajectory points corresponding to the suspected missing road;

[0032] Determine the connectability between each target trajectory point and adjacent target trajectory points according to the distribution density of the target trajectory points;

[0033] Connect a plurality of connectable target trajectory points to form a trajectory point cluster corresponding to the suspected missing road.

[0034] In some exemplary embodiments of the present disclosure, based on the above technical solutions, obtaining the motion trajectory information of the target object includes:

[0035] Obtain the motion trajectory information of the target object within a target map range and a target time range.

[0036] In some exemplary embodiments of the present disclosure, based on the above technical solutions, determining the motion trajectory points of the target object on the map according to the motion trajectory information includes:

[0037] Determine the initial position of the target object on the map according to the motion trajectory information, and use the initial position as the first motion position node of the target object;

[0038] Starting from the initial position, sequentially select a plurality of motion position nodes of the target object along the motion trajectory of the target object, and determine the motion position nodes as the motion trajectory points of the target object on the map.

[0039] In some exemplary embodiments of the present disclosure, based on the above technical solutions, a plurality of motion position nodes of the target object are sequentially selected along the motion trajectory of the target object, including:

[0040] Select a temporary position node of the target object along the motion trajectory of the target object;

[0041] Obtain the motion distance and motion time between the temporary position node and the previous motion position node of the target object;

[0042] When the motion distance is greater than the target distance interval or the motion time is greater than the target time interval, determine the temporary position node as the motion position node of the target object;

[0043] Continue to select the next temporary position node of the target object along the motion trajectory of the target object to determine the next motion position node of the target object.

[0044] In some exemplary embodiments of the present disclosure, based on the above technical solutions, the motion trajectory points are screened according to the positional relationship between the trajectory points and the existing roads on the map to obtain target trajectory points corresponding to suspected missing roads, including:

[0045] Determine the adjacent road closest to the motion trajectory point according to the positional relationship between the motion trajectory point and the existing roads on the map;

[0046] When the distance between the motion trajectory point and the adjacent road is greater than the target road distance, determine the motion trajectory point as the target trajectory point corresponding to the suspected missing road.

[0047] In some exemplary embodiments of the present disclosure, based on the above technical solutions, before screening the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain target trajectory points corresponding to suspected missing roads, the method further includes:

[0048] Obtain the motion speed and positioning error of each of the motion trajectory points;

[0049] Mark the motion trajectory points with a motion speed less than the speed limit value or a positioning error greater than the error limit value as noise trajectory points;

[0050] Remove the noise trajectory points from the motion trajectory points.

[0051] According to one aspect of the present disclosure, there is provided an apparatus for determining missing roads on a map, the apparatus including:

[0052] A point cluster determination module, configured to determine a trajectory point cluster corresponding to a suspected missing road, which is composed of a plurality of motion trajectory points;

[0053] An information acquisition module, configured to acquire the motion position information and motion direction information of each of the motion trajectory points in the trajectory point cluster;

[0054] A confidence determination module, configured to determine the road confidence that the suspected missing road is a map missing road according to the motion position information and the motion direction information.

[0055] According to one aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored. The special feature is that when the computer program is executed by a processor, it implements the method for determining a map missing road as described in any one of the above.

[0056] According to one aspect of the present disclosure, there is provided an electronic device, which is characterized in that it includes a processor and a memory; wherein, the memory is used to store executable instructions of the processor, and the processor is configured to execute the method for determining a map missing road as described in any one of the above by executing the executable instructions.

[0057] In an exemplary embodiment of the present disclosure, by acquiring the motion position information and motion direction information of motion trajectory points to calculate the road confidence that a suspected missing road is an actual map missing road, the true credibility of the map missing road can be quantitatively characterized. Within a relatively high confidence interval, the accuracy of the map missing road can be ensured without relying on manual review. This method can not only save a large amount of labor costs, but also greatly improve the determination efficiency and accuracy of map missing roads, so as to automatically and efficiently complete the road network of the electronic map accurately.

[0058] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 It shows a flowchart of the steps of the method for determining a map missing road in some exemplary embodiments of the present disclosure.

[0061] Figure 2The flowchart shows the steps of determining road confidence in some exemplary embodiments of the present disclosure.

[0062] Figure 3 The flowchart shows the steps of determining the dispersion of a cluster of trajectory points in some exemplary embodiments of the present disclosure.

[0063] Figure 4 The flowchart shows the steps of determining the disorder degree of a cluster of trajectory points in some exemplary embodiments of the present disclosure.

[0064] Figure 5 The flowchart shows the steps of determining a direction interval in some exemplary embodiments of the present disclosure.

[0065] Figure 6 The flowchart shows the steps of determining road confidence based on dispersion and disorder degree in some exemplary embodiments of the present disclosure.

[0066] Figure 7 The flowchart shows the steps of determining a cluster of trajectory points in some exemplary embodiments of the present disclosure.

[0067] Figure 8 The flowchart shows the steps of determining a moving trajectory point in some exemplary embodiments of the present disclosure.

[0068] Figure 9 The flowchart shows the steps of selecting a moving position node from the moving trajectory of a target object in some exemplary embodiments of the present disclosure.

[0069] Figure 10 The flowchart shows the steps of screening target trajectory points in some exemplary embodiments of the present disclosure.

[0070] Figure 11 The flowchart shows the steps of clearing noise trajectory points in some exemplary embodiments of the present disclosure.

[0071] Figure 12 The flowchart shows the steps of the method for determining missing roads on a map in an application scenario in some exemplary embodiments of the present disclosure.

[0072] Figure 13 The schematic diagram shows the clustering effect of clustering sample points by the DBSCAN clustering algorithm.

[0073] Figure 14 The schematic diagram shows the distribution state of a cluster of trajectory points on an electronic map.

[0074] Figure 15 The schematic diagram shows the suspected missing road position corresponding to a cluster of trajectory points.

[0075] Figure 16 The block diagram of the device for determining missing roads in a map according to an exemplary embodiment of the present disclosure is shown.

[0076] Figure 17 The schematic diagram of a program product according to an exemplary embodiment of the present disclosure is shown.

[0077] Figure 18 The module schematic diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown. Detailed implementation manners

[0078] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0079] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0080] According to one aspect of the exemplary embodiments of the present disclosure, first, a method for determining missing roads in a map is provided. This method is used to determine the missing roads in an electronic map and evaluate the true credibility of the missing roads, so as to efficiently and accurately complete the missing roads in the electronic map.

[0081] Figure 1 The step flowchart of the method for determining missing roads in a map in some exemplary embodiments of the present disclosure is shown. As Figure 1 shown, the method mainly may include the following steps:

[0082] Step S110. Determine a cluster of trajectory points corresponding to a suspected missing road, which is composed of a plurality of motion trajectory points.

[0083] The moving trajectory points are mainly map location points distributed on the electronic map formed by a moving object during its movement. The moving object can be a motor vehicle equipped with a navigation device, an express delivery during transportation, a food delivery rider, etc. Additionally, it can also be a terminal device equipped with an electronic map or other application programs with the permission to obtain the user's location. By obtaining the map location information of the moving object, moving trajectory points distributed along the moving trajectory can be formed on the electronic map. The vast majority of these moving trajectory points are distributed on the existing road network of the electronic map. For the moving trajectory points that appear on non-existing road networks, their locations may be real roads missing from the electronic map, but they may also be moving trajectories on non-real roads caused by positioning errors, data errors, or the random crossing of the moving object. Therefore, these moving trajectory points that appear on non-existing road networks can form a cluster of trajectory points corresponding to the suspected missing road.

[0084] Step S120. Obtain the movement position information and movement direction information of each moving trajectory point in the cluster of trajectory points.

[0085] After determining the cluster of trajectory points corresponding to the suspected missing road, this step will obtain the movement position information and movement direction information of all the moving trajectory points in this cluster of trajectory points. Among them, the movement position information can be the longitude and latitude directly obtained from the map location data, or the position coordinate data formed in the self-built coordinate system of the electronic map. The movement direction information can be the instantaneous movement direction of the moving trajectory point, or the average movement direction determined by the position relationship of multiple moving trajectory points within a certain movement duration.

[0086] Step S130. Determine the road confidence level that the suspected missing road is a road missing from the map based on the movement position information and the movement direction information.

[0087] The movement position information and movement direction information of each moving trajectory point in the cluster of trajectory points can, to a certain extent, reflect the credibility of the location where the cluster of trajectory points is located as a real road. In this step, by analyzing and processing the movement position information and movement direction information, the road confidence level that the suspected missing road corresponding to the cluster of trajectory points is a real road missing from the map can be obtained. The higher the road confidence level, the greater the possibility that the suspected missing road is an actual missing road. The determination method of the road confidence level can be to establish a calculation model related to the two parameters of movement position and movement direction, and then use this calculation model to calculate the road confidence level in combination with the movement position information and movement direction information obtained in step S120. Additionally, in this exemplary embodiment, a machine learning model for calculating the road confidence level can also be pre-trained, and then the movement position information and movement direction information obtained in step S120 are input into this machine learning model, and it outputs the road confidence level that the suspected missing road is a road missing from the map.

[0088] In the method for determining a missing road in a map provided by this exemplary embodiment, by obtaining the movement position information and movement direction information of movement trajectory points to calculate the road confidence level of a suspected missing road being an actual missing road in the map, the true credibility of the missing road in the map can be quantitatively characterized. Within a relatively high confidence interval, the accuracy of the missing road in the map can be ensured without relying on manual review. This method can not only save a large amount of labor costs, but also greatly improve the determination efficiency and accuracy of the missing road in the map, thereby enabling the automatic and efficient and accurate road network completion of the electronic map.

[0089] Figure 2 The flowchart of steps for determining the road confidence level in some exemplary embodiments of the present disclosure is shown.

[0090] As Figure 2 shown, based on the above exemplary embodiments, step S130. Determine the road confidence level of a suspected missing road being a missing road in the map according to the movement position information and movement direction information, which may include the following steps:

[0091] Step S210. Determine the dispersion degree of the trajectory point cluster representing the position dispersion degree between each movement trajectory point according to the movement position information.

[0092] The dispersion degree of the trajectory point cluster is used to represent the position dispersion degree between each movement trajectory point in the trajectory point cluster. The lower the dispersion degree of the trajectory point cluster, the higher the position aggregation degree of the movement trajectory points inside it. For an actual missing road in the map, generally, there will be relatively more moving objects frequently appearing at its location, that is, a trajectory point cluster with a relatively high degree of aggregation of movement trajectory points will be formed at its location. Therefore, the dispersion degree of the trajectory point cluster can reflect to a certain extent the true credibility of the suspected missing road being a missing road in the map.

[0093] Step S220. Determine the disorder degree of the trajectory point cluster representing the direction disorder degree of each movement trajectory point according to the movement direction information.

[0094] The disorder degree of the trajectory point cluster is used to represent the direction disorder degree between each movement trajectory point in the trajectory point cluster. The lower the disorder degree of the trajectory point cluster, the higher the direction order degree of the movement trajectory points inside it. For an actual missing road in the map, moving objects located on a straight road generally only move along the forward and reverse directions of the road, that is, a trajectory point cluster with a highly ordered movement direction of movement trajectory points will be formed at its location. Therefore, the disorder degree of the trajectory point cluster can also reflect to a certain extent the true credibility of the suspected missing road being a missing road in the map.

[0095] Step S230. Determine the road confidence level that the suspected missing road is a map missing road based on the dispersion degree and the disorder degree.

[0096] Based on the dispersion degree of the trajectory point clusters obtained in step S210 and the disorder degree of the trajectory point clusters obtained in step S220, this step can determine the road confidence level that the suspected missing road is a map missing road. Generally speaking, when the dispersion degree and the disorder degree are lower, the true credibility that the suspected missing road is a map missing road is higher, that is, the road confidence level is higher.

[0097] By calculating the two parameters of the dispersion degree and the disorder degree of the trajectory point clusters, the true credibility that the suspected missing road is a map missing road can be evaluated from different dimensions, thereby improving the reliability and robustness of the road confidence level.

[0098] The determination methods of the two parameters of the dispersion degree and the disorder degree are described below respectively.

[0099] Figure 3 The flowchart of the steps for determining the dispersion degree of the trajectory point clusters in some exemplary embodiments of the present disclosure is shown.

[0100] As Figure 3 shown, based on the above exemplary embodiments, step S210. Determine the dispersion degree of the trajectory point clusters for representing the position dispersion degree between each movement trajectory point according to the movement position information, which may include the following steps:

[0101] Step S310. Determine the position distance between each movement trajectory point and each other movement trajectory point according to the movement position information of each movement trajectory point.

[0102] A position distance can be determined between any two movement trajectory points in the trajectory point clusters. Optionally, in this step, the actual spherical distance on the earth can be calculated as the position distance between the two movement trajectory points according to the longitude and latitude data of the two movement trajectory points, and alternatively, the planar distance can be calculated as the position distance between the two movement trajectory points according to the position coordinates of the two movement trajectory points in the self-built coordinate system of the map.

[0103] Step S320. Determine the trajectory point dispersion degree of each movement trajectory point in the trajectory point clusters according to the position distance.

[0104] According to the position distance between a movement trajectory point and other movement trajectory points, the trajectory point dispersion degree of this movement trajectory point can be determined, and the trajectory point dispersion degree reflects the dispersion degree of other movement trajectory points in the trajectory point clusters relative to this movement trajectory point. For each movement trajectory point in the trajectory point clusters, a corresponding trajectory point dispersion degree can be determined.

[0105] Step S330. Determine the dispersion degree of the trajectory point cluster representing the positional dispersion degree among the respective motion trajectory points according to the trajectory point dispersion degree of the motion trajectory points.

[0106] According to the trajectory point dispersion degrees of the respective motion trajectory points in the trajectory point cluster determined in step S320, this step can integrate them to obtain the overall dispersion degree of the trajectory point cluster, which reflects the positional dispersion degree among the respective motion trajectory points within the trajectory point cluster. Optionally, this step can directly take the average of the trajectory point dispersion degrees of the respective motion trajectory points as the overall dispersion degree of the trajectory point cluster.

[0107] Figure 4 The flowchart shows the steps of determining the disorder degree of the trajectory point cluster in some exemplary embodiments of the present disclosure.

[0108] As Figure 4 shown, based on the above exemplary embodiments, step S220. Determine the disorder degree of the trajectory point cluster representing the directional disorder degree of the respective motion trajectory points according to the motion direction information, which may include the following steps:

[0109] Step S410. Determine a plurality of direction intervals corresponding to different direction ranges.

[0110] To effectively characterize and distinguish the motion directions of the respective motion trajectory points, this step first determines a plurality of direction intervals covering different direction ranges. Referring to Figure 5 shown, the method for determining the direction intervals in this step may specifically include the following steps:

[0111] Step S510. Determine the direction range covering all motion directions on the map plane.

[0112] For example, taking the due north direction as the 0-degree direction, then the entire map plane will cover a direction range of 0 to 360 degrees. The rotation angle along the clockwise direction between each direction and the due north direction can be used as the measurement angle value of this direction. For example, the due east direction corresponds to the 90-degree direction, the due south direction corresponds to the 180-degree direction, and the due west direction corresponds to the 270-degree direction.

[0113] Step S520. Divide the direction range into a plurality of direction intervals with the same range size.

[0114] This step can evenly divide the overall direction range into n direction intervals, then each direction interval will cover a direction range with an angle value interval of 360 / n. Optionally, this step can determine 8 direction intervals, then each direction interval will cover a 45-degree direction range.

[0115] Step S420. Divide each motion trajectory point in the trajectory point cluster into a direction interval according to the motion direction information.

[0116] According to the motion direction information of the motion trajectory points in the trajectory point cluster, the motion trajectory points can be divided into direction intervals. For example, if the motion direction of a certain motion trajectory point is 30 degrees east of north, then this motion trajectory point can be divided into the direction interval of 0 to 45 degrees; if the motion direction of another motion trajectory point is 30 degrees south of east, then this motion trajectory point can be divided into the direction interval of 90 to 135 degrees.

[0117] Step S430. Determine the quantity ratio between the motion trajectory points in each direction interval and all the motion trajectory points in the trajectory point cluster according to the division result of the direction interval.

[0118] After step S420 completes the division of the direction intervals of each motion trajectory point, this step can count the number of motion trajectory points falling within each direction interval and the total number of motion trajectory points in the trajectory point cluster. The quantity ratio between the two is the quantity proportion of the motion trajectory points in each direction interval.

[0119] Step S440. Determine the disorder degree of the trajectory point cluster used to represent the direction disorder degree of each motion trajectory point according to the quantity ratio.

[0120] According to the quantity ratio of the motion trajectory points in each direction interval, the disorder degree of the trajectory point cluster can be determined. This disorder degree is used to represent the direction disorder degree among each motion trajectory point. The disorder degree of the trajectory point cluster is similar to entropy in thermodynamics. Entropy is a physical parameter used to characterize the degree of chaos of a system. In molecular thermal motion, the numerical value of entropy can describe the disorder degree of the motion direction of molecules. In this exemplary embodiment, the concept of entropy can be used to characterize the direction disorder degree of the motion trajectory points.

[0121] For a real missing road on the map, more motion trajectory points should fall into the direction interval corresponding to the road driving direction, while there are no or only a small number of motion trajectory points falling into other direction intervals. Thus, it can be seen that the lower the disorder degree of the trajectory point cluster, the higher the possibility that the corresponding suspected missing road is a real missing road on the map.

[0122] Figure 6 Shows a flowchart of steps for determining road confidence according to the dispersion degree and disorder degree in some exemplary embodiments of the present disclosure.

[0123] As Figure 6As shown, based on the above exemplary embodiments, step S330 of determining the dispersion degree of the trajectory point cluster representing the position dispersion degree between each motion trajectory point according to the trajectory point dispersion degree of the motion trajectory points may include the following steps:

[0124] Step S610. After respectively normalizing the dispersion degree and the disorder degree, the normalized dispersion degree and the normalized disorder degree are obtained.

[0125] For the dispersion degree and the disorder degree respectively determined through step S310 and step S320, since the determination of the two parameters is carried out independently, there are also significant differences in the value ranges of the parameters. In order to unify the two for facilitating the determination of the road confidence level, this step may first normalize the dispersion degree to obtain the normalized dispersion degree, and at the same time normalize the disorder degree to obtain the normalized disorder degree, so that two parameters with consistent value ranges can be obtained.

[0126] Step S620. Determine the road confidence level that the suspected missing road is a map missing road according to the normalized dispersion degree and the normalized disorder degree.

[0127] Compared with the dispersion degree and the disorder degree with uncertain value ranges, calculating the road confidence level based on the normalized dispersion degree and the normalized disorder degree can enable two evaluation parameters of different dimensions to occupy a relatively balanced influence degree in the road confidence level, so that a relatively objective calculation result can be obtained.

[0128] Figure 7 Shows a flowchart of steps for determining a trajectory point cluster in some exemplary embodiments of the present disclosure.

[0129] As Figure 7 shown, step S110 of determining the trajectory point cluster corresponding to the suspected missing road composed of multiple motion trajectory points may include the following steps:

[0130] Step S710. Obtain the motion trajectory information of the target object, and determine the motion trajectory points of the target object on the map according to the motion trajectory information.

[0131] This step may first select one or several motion objects as the target object. For example, a food delivery rider may be used as the target object. By collecting the navigation and positioning data of the food delivery rider, the motion trajectory information thereof is obtained. According to the obtained motion trajectory information of the target object, the motion trajectory points of the target object on the map can be determined. The motion trajectory points are independent nodes located on the motion trajectory of the target object, and the determination result of the motion trajectory points is related to data collection methods such as the collection range and collection frequency of the navigation and positioning data.

[0132] Optionally, in this step, the movement trajectory information of the target object within the target map range and within the target time range can be obtained as the basis for determining the movement trajectory points. For example, in this step, the movement trajectory information of food delivery riders within the urban area of Beijing within one week can be obtained, and the movement trajectory points can be determined based on this part of the information. Determining a suitable target map range can increase the possibility of discovering suspected missing roads from the electronic map; while determining a suitable target time range can improve the accuracy of judging whether a suspected missing road is a real map missing road.

[0133] Step S720. Screen the movement trajectory points according to the positional relationship between the movement trajectory points and the existing roads on the map to obtain target trajectory points corresponding to the suspected missing roads.

[0134] In this step, the existing road network information on the map can be obtained, and the positional relationship between the movement trajectory points and the existing roads can be determined based on the existing road network information. According to this positional relationship, the movement trajectory points can be screened, and the target trajectory points corresponding to the suspected missing roads can be selected from them. For example, for the movement trajectory points distributed on the existing roads or close to the existing roads in terms of position, it can be considered that the target object is moving on the existing roads, so they need to be excluded. For the movement trajectory points far from the existing roads in terms of position, it can be preliminarily judged that the moving object is moving on the suspected missing road, so they can be used as the target trajectory points.

[0135] Step S730. Determine the connectability between each target trajectory point and its adjacent target trajectory points according to the distribution density of the target trajectory points.

[0136] According to the distribution quantity of other target trajectory points within a certain range around a target trajectory point, the distribution density of this target trajectory point can be determined. Then, according to the numerical relationship of the distribution density, the connectability between each target trajectory point and its neighboring other target trajectory points can be determined. For example, the target trajectory points with a distribution density greater than a certain value can be determined as connectable, while the other target trajectory points with a smaller distribution density can be determined as non-connectable. For example, there are 4 other target trajectory points distributed within 10 meters around a certain target trajectory point, then its distribution density can be recorded as 4. For the other four neighboring target trajectory points, their distribution densities can be determined in the same way as 2, 1, 5, and 3 respectively. Then, the target trajectory point with a distribution density of 5 can be used as the connectable target trajectory point, while the other three target trajectory points with a distribution density less than 4 are used as non-connectable target trajectory points.

[0137] Step S740. Connect multiple connectable target trajectory points to form a trajectory point cluster corresponding to the suspected missing road.

[0138] After obtaining the distribution density of each target trajectory point and determining the connectivity between each target trajectory point and other adjacent target trajectory points, this step will connect the connectable target trajectory points to form a trajectory point cluster corresponding to the suspected missing road. Some other target trajectory points that are relatively close can also fall within the range of the trajectory point cluster, while those that are relatively far away will be excluded from the trajectory point cluster.

[0139] In this exemplary embodiment, by determining the distribution density to judge the connectivity of the target trajectory points, the area with a higher distribution density can be included in the range of the trajectory point cluster, and a trajectory point cluster of any shape can be formed, which is beneficial to discovering the missing roads on the map with diverse shapes.

[0140] Figure 8 The flowchart shows the steps of determining the movement trajectory points in some exemplary embodiments of the present disclosure.

[0141] As Figure 8 shown, based on the above exemplary embodiment, determining the movement trajectory points of the target object on the map according to the movement trajectory information in step S710 may include the following steps:

[0142] Step S810. Determine the initial position of the target object on the map according to the movement trajectory information, and use the initial position as the first movement position node of the target object.

[0143] After determining the subsequent movement trajectory information of the target object, especially in the case of determining the target map range and the target time range, this step can determine the initial position of the target object on the map. This initial position can be the position where the target object first appears on the map within the target map range and the target time range, and this position is also used as the first movement position node of the target object.

[0144] Step S820. Starting from the initial position, sequentially select multiple movement position nodes of the target object along the movement trajectory of the target object, and determine the movement position nodes as the movement trajectory points of the target object on the map.

[0145] As the target object moves, a movement trajectory starting from the initial position will be left on the map. Starting from the initial position of the target object, multiple movement position nodes can be sequentially selected along the movement trajectory of the target object. The selected movement position nodes are determined as the movement trajectory points of the target object on the map.

[0146] Figure 9 The flowchart shows the steps of selecting movement position nodes from the movement trajectory of the target object in some exemplary embodiments of the present disclosure.

[0147] As Figure 9As shown, the step of sequentially selecting multiple motion position nodes of the target object along the motion trajectory in step S820 may include the following steps:

[0148] Step S910. Select a temporary position node of the target object along the motion trajectory of the target object.

[0149] The motion trajectory of the target object consists of a series of position nodes. In this step, a temporary position node can be selected along the motion trajectory of the target object. For example, after determining a motion position node, the first position node recorded after this motion position node can be used as the selected temporary position node.

[0150] Step S920. Obtain the motion distance and motion time between the temporary position node and the previous motion position node of the target object.

[0151] Each motion position node and temporary position node on the motion trajectory of the target object has position information and time information generated by map positioning. After determining the temporary position node, the motion distance and motion time between this temporary position node and the previous motion position node can be obtained according to the corresponding positioning data. Among them, the motion distance can be the trajectory length on the motion trajectory.

[0152] Step S930. When the motion distance is greater than the target distance interval or the motion time is greater than the target time interval, determine the temporary position node as the motion position node of the target object.

[0153] Make a judgment on the motion distance and motion time obtained in step S920. If the motion distance between a temporary position node and the previous motion position node is greater than the target distance interval or the motion time between this temporary position node and the previous motion position node is greater than the target time interval, then this temporary position node can be determined as a new motion position node. In other words, as long as any one of the two parameters of motion distance and motion time reaches the target value, a motion position node can be selected.

[0154] Step S940. Continue to select the next temporary position node of the target object along the motion trajectory of the target object to determine the next motion position node of the target object.

[0155] After determining a new motion position node, steps S910 to S930 can be returned and continued. That is, continue to select the next temporary position node and then determine the next motion position node. By repeatedly executing the step of determining the motion position node, multiple motion position nodes can be sequentially selected along the motion trajectory of the target object until reaching the motion end point of the target object within the specified time and geographical range.

[0156] In the present exemplary embodiment, using the target distance interval and the target time interval as the basis for selecting the motion position nodes, relatively evenly distributed motion position nodes can be obtained. For example, if the motion speed of the target object is relatively fast, the condition of the target distance interval will be satisfied first; if the motion speed of the target object is relatively slow, the condition of the target time interval will be satisfied first. Therefore, regardless of how the motion speed of the target object changes, the situation where the motion position nodes are too dense or too sparse can be effectively avoided, thereby improving the effectiveness and representativeness of each motion position node as a motion trajectory point.

[0157] Figure 10 The flowchart showing the steps of screening target trajectory points in some exemplary embodiments of the present disclosure is shown.

[0158] As Figure 10 shown, based on the above exemplary embodiment, step S720. Screening the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain the target trajectory points corresponding to the suspected missing roads may include the following steps:

[0159] Step S1010. Determine the neighboring road closest to the motion trajectory point according to the positional relationship between the motion trajectory point and the existing roads on the map.

[0160] For the motion trajectory points distributed on the existing roads of the map, the road where they are located is the neighboring road closest to them (i.e., the distance is zero); for the motion trajectory points distributed outside the existing roads, the perpendicular distance between the motion trajectory point and multiple existing roads distributed around it in the map plane can be determined, and the closest existing road is used as its neighboring road.

[0161] Step S1020. When the distance between the motion trajectory point and the neighboring road is greater than the target road distance, determine the motion trajectory point as the target trajectory point corresponding to the suspected missing road.

[0162] If the distance between a motion trajectory point and the neighboring road is greater than the target road distance (for example, greater than 30 meters), then the position where the motion trajectory point is located can be regarded as the position of the suspected missing road, and the motion trajectory point can also be determined as the target trajectory point corresponding to the suspected missing road. If the distance between a motion trajectory point and the neighboring road is very short, then the motion trajectory point is likely to be caused by positioning errors, and the corresponding target object is likely to be moving on the neighboring existing road rather than the suspected missing road. By setting the target road distance, this part of the motion trajectory points generated due to inaccurate positioning can be excluded from the target trajectory points.

[0163] Invalid motion trajectory points caused by inaccurate positioning or other reasons can be regarded as noise trajectory points that need to be cleared. Figure 11 FIG. shows a flowchart of steps for clearing noise trajectory points in some exemplary embodiments of the present disclosure.

[0164] As Figure 11 shown, based on the above exemplary embodiments, before step S720. Screening the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain target trajectory points corresponding to suspected missing roads, the following steps may also be performed:

[0165] Step S1110. Obtain the motion speed and positioning error of each motion trajectory point.

[0166] The motion speed and positioning error of each motion trajectory point can be obtained by collecting map positioning data. Among them, the motion speed can be the instantaneous speed of the target object at the position where the motion trajectory point is located, and the positioning error can be the distance error between the positioning position and the real position of the target object.

[0167] Step S1120. Mark the motion trajectory points with a motion speed less than the speed limit or a positioning error greater than the error limit as noise trajectory points.

[0168] Noise trajectory points in the motion trajectory points can be determined according to the magnitudes of the motion speed and the positioning error. If the motion speed of a motion trajectory point is less than the speed limit (such as less than 1 m / s), then the motion speed of the target object is too slow to reflect the representativeness of the normal motion of the motion trajectory point on the road. If the positioning error of a motion trajectory point is greater than the error limit (such as greater than 8 m), then the positioning accuracy of this motion trajectory point is relatively low and it cannot provide effective positioning data.

[0169] Step S1130. Clear the noise trajectory points in the motion trajectory points.

[0170] Through step S1120, the noise trajectory points in the motion trajectory points can be marked, and this step will clear this part of the noise trajectory points, so as to ensure that the remaining motion trajectory points can provide positioning data with a certain degree of representativeness and effectiveness, thereby improving the accuracy of determining the road confidence level.

[0171] Next, with reference to Figure 12 , the step flow of the method for determining missing roads on the map provided by the exemplary embodiments of the present disclosure in an application scenario will be described. In this application scenario, a food delivery rider responsible for food delivery is used as the target object. Based on the GPS trajectory data of the food delivery rider, the missing routes are mined through a data mining algorithm, and the confidence value of the road is output, and the roads with higher confidence are selected for automatic road network completion.

[0172] As Figure 12 shown, the method for determining the missing roads on the map mainly includes the following parts:

[0173] First, preprocess the GPS trajectory data of food delivery riders:

[0174] Step S1210. Import data from the data warehouse system.

[0175] Use an X86 architecture Linux operating system server cluster to build a distributed scientific computing system with Spark, import and store the rider riding trajectory data in the data warehouse system in units of 14 natural days for each city. The trajectory density is one trajectory point per 100 meters or 60 seconds for each rider (whichever comes first). The data of each trajectory point includes: longitude, latitude, movement speed, movement direction, and positioning error.

[0176] Step S1220. Clean high-error data.

[0177] Data that does not meet the requirements can be classified into several categories such as incomplete, inconsistent, and noise data. Different treatments can be adopted for each type of data. Since GPS data itself is a kind of noise data, high-error trajectory point records need to be deleted. For example, trajectory point records with a positioning error greater than 8 meters and a movement speed less than 1 m / s can be deleted.

[0178] Step S1230. Screen trajectory records not in the existing road network.

[0179] Screen out the trajectory point records with a perpendicular projection distance greater than 30 meters from the existing road network as the effective data after cleaning.

[0180] After obtaining the effective data through preprocessing, trajectory point clusters can be determined by the density clustering algorithm.

[0181] Step S1240. Density clustering.

[0182] Clustering is a task of grouping samples, making similar objects belong to one class and dissimilar objects belong to different classes. Density clustering examines the connectability between samples from the perspective of sample density, and continuously expands from the connectable samples until the final clustering result is obtained.

[0183] Figure 13 shows the clustering effect of clustering sample points using the DBSCAN clustering algorithm. In Figure 13 the case of the sample point distribution shown, first determine a fixed circular radius, and then take the sample points with a sample density greater than 4 within the circular range as the connectable sample points, and connect each connectable sample point in turn to obtain as Figure 13Two clusters of sample points respectively along the paths of the two arrow connection lines shown.

[0184] In the application scenario of the present disclosure, the DBSCAN clustering algorithm model can be established using the Spark development platform, the trajectory point record data generated through data preprocessing is imported, and calculations are performed according to the model rules, and finally a cluster of trajectory points corresponding to the suspected missing road is generated.

[0185] As Figure 14 shown, on the electronic map, a density clustering algorithm can be used to determine a cluster of trajectory points (other trajectory points outside this cluster of trajectory points are not shown in the figure), and this cluster of trajectory points corresponds to Figure 15 a suspected missing road (the position where the ellipse is located) shown.

[0186] After density clustering processing, a set of trajectory divisions for the suspected missing road has been generated. Next, it is necessary to further calculate the confidence parameter of the suspected missing road being a real map missing road.

[0187] Step S1250. Calculation of dispersion.

[0188] Dispersion can be understood as the within-cluster dissimilarity of each cluster of trajectory points in the division of the missing road trajectory points. Its calculation method is as follows:

[0189] Let the set of trajectory points contained in cluster i of trajectory points be E = (X 1 , X 2 ,..., X j ), and the calculation method of the cohesion of point X n is:

[0190]

[0191] where Distance() is used to calculate the actual spherical distance between two trajectory points, and a distance calculation method similar to that in the density clustering part can be adopted.

[0192] The overall cohesion of cluster i of trajectory points is:

[0193]

[0194] Calculate the dispersion of all clusters of trajectory points respectively, and a data set C = {C 1 , C 2 ,..., C m} can be obtained.

[0195] Step S1260. Divide the direction interval.

[0196] This disclosure quantifies the degree of disorder of the directions of each trajectory point in the set of trajectory point clusters based on the calculation principle of thermal entropy used to characterize the state of matter in thermodynamics. On this basis, the direction interval is first divided.

[0197] The direction data of each trajectory point in the trajectory point cluster forms a range interval of 0 to 360 degrees with the due north direction as 0 degrees. The direction values are evenly divided into n intervals, with 360 / n as the interval length. For example, when n = 8, the interval length is 360 / 8 = 45, and thus the interval division of the direction of each trajectory point in the set of trajectory point clusters is calculated.

[0198] Step S1270. Divide the direction interval.

[0199] Let the set of trajectory points included in trajectory point cluster i be E = (X 1 , X 2 ,..., X j ), n be the number of divided intervals, and p k be the probability that the trajectory points in the k-th divided interval account for all the trajectory points in this trajectory point cluster. Then the calculation method of the degree of disorder of trajectory point cluster i is:

[0200]

[0201] Calculate the degrees of disorder of all trajectory point clusters respectively, and the data set En = {En 1 , En 2 ,..., En m} can be obtained.

[0202] Step S1280. Calculate the confidence level.

[0203] The overall dispersion degree of trajectory point cluster i after normalization is:

[0204]

[0205] The overall degree of disorder of trajectory point cluster i after normalization is:

[0206]

[0207] The confidence level of trajectory point cluster i is:

[0208]

[0209] Calculate the confidence levels of all trajectory point clusters respectively, and the data set Fn = {Fn 1 , Fn 2 ,..., Fn m}, and store it on the Hadoop Distributed File System (HDFS). The higher the confidence value, the greater the likelihood that the suspected missing road corresponding to the trajectory point cluster is an actual missing road on the map. Within a relatively high confidence interval, the correctness can be ensured without relying on manual review, significantly improving the efficiency of missing road excavation, and thus it can be used to solve the problem of automatically completing the road network.

[0210] It should be noted that although the above exemplary embodiments describe the steps of the methods in the present disclosure in a specific order, this does not require or imply that these steps must be executed in this specific order, or that all steps must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0211] In an exemplary embodiment of the present disclosure, there is also provided a device for determining missing roads on a map. Figure 16 The composition structure of the device is shown.

[0212] As Figure 16 shown, the device 1600 for determining missing roads on a map mainly includes: a point cluster determination module 1610, an information acquisition module 1620, and a confidence determination module 1630.

[0213] The point cluster determination module 1610 is configured to determine a trajectory point cluster corresponding to a suspected missing road, which is composed of multiple motion trajectory points;

[0214] The information acquisition module 1620 is configured to acquire the motion position information and motion direction information of each of the motion trajectory points in the trajectory point cluster;

[0215] The confidence determination module 1630 is configured to determine the road confidence of the suspected missing road as a missing road on the map according to the motion position information and the motion direction information.

[0216] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the confidence determination module 1630 may further include:

[0217] A dispersion determination unit, configured to determine the dispersion of the trajectory point cluster for representing the degree of position dispersion between each of the motion trajectory points according to the motion position information;

[0218] A disorder determination unit, configured to determine the disorder of the trajectory point cluster for representing the degree of direction disorder of each of the motion trajectory points according to the motion direction information;

[0219] A confidence determination unit configured to determine a road confidence that the suspected missing road is a map missing road according to the dispersion degree and the disorder degree.

[0220] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the dispersion degree determination unit may further include:

[0221] A position distance determination subunit configured to determine a position distance between each of the motion trajectory points and each of the other motion trajectory points according to the motion position information of each of the motion trajectory points;

[0222] A trajectory point dispersion degree determination subunit configured to determine a trajectory point dispersion degree of each of the motion trajectory points in the trajectory point cluster according to the position distance;

[0223] A dispersion degree determination subunit configured to determine a dispersion degree of the trajectory point cluster for representing a position dispersion degree between each of the motion trajectory points according to the trajectory point dispersion degree of the motion trajectory points.

[0224] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the disorder degree determination unit may further include:

[0225] A direction interval determination subunit configured to determine a plurality of direction intervals corresponding to different direction ranges;

[0226] A reverse interval division subunit configured to divide each of the motion trajectory points in the trajectory point cluster into the direction intervals according to the motion direction information;

[0227] A quantity ratio determination subunit configured to determine a quantity ratio between the motion trajectory points in each of the direction intervals and all the motion trajectory points in the trajectory point cluster according to the division result of the direction intervals;

[0228] A disorder degree determination subunit configured to determine a disorder degree of the trajectory point cluster for representing a direction disorder degree of each of the motion trajectory points according to the quantity ratio.

[0229] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the direction interval determination subunit may further include:

[0230] A direction range determination grandchild subunit configured to determine a direction range covering all motion directions on the map plane;

[0231] A direction interval determination grandchild subunit configured to divide the direction range into a plurality of direction intervals having the same range size.

[0232] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the confidence determination unit may further include:

[0233] A normalization determination subunit, configured to perform normalization processing on the dispersion degree and the disorder degree respectively to obtain a normalized dispersion degree and a normalized disorder degree;

[0234] A confidence determination subunit, configured to determine the road confidence that the suspected missing road is a map missing road according to the normalized dispersion degree and the normalized disorder degree.

[0235] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the point cluster determination module 1610 may further include:

[0236] A motion trajectory point determination unit, configured to obtain the motion trajectory information of a target object and determine the motion trajectory points of the target object on the map according to the motion trajectory information;

[0237] A target trajectory point determination unit, configured to screen the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain target trajectory points corresponding to the suspected missing roads;

[0238] A connectability determination unit, configured to determine the connectability between each of the target trajectory points and adjacent target trajectory points according to the distribution density of the target trajectory points;

[0239] A trajectory point cluster determination unit, configured to connect multiple connectable target trajectory points to form a trajectory point cluster corresponding to the suspected missing road.

[0240] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the motion trajectory point determination unit may further include:

[0241] A motion trajectory information acquisition subunit, configured to acquire the motion trajectory information of a target object within a target map range and within a target time range.

[0242] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the motion trajectory point determination unit may further include:

[0243] An initial position determination subunit, configured to determine the initial position of the target object on the map according to the motion trajectory information and use the initial position as the first motion position node of the target object;

[0244] The motion trajectory point determination subunit is configured to sequentially select multiple motion position nodes of the target object along the motion trajectory of the target object starting from the initial position, and determine the motion position nodes as the motion trajectory points of the target object on the map.

[0245] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the motion trajectory point determination subunit may further include:

[0246] The temporary position node determination grandchild unit is configured to select a temporary position node of the target object along the motion trajectory of the target object;

[0247] The distance and time acquisition grandchild unit is configured to acquire the motion distance and motion time between the temporary position node and the previous motion position node of the target object;

[0248] The motion position node determination grandchild unit is configured to determine the temporary position node as the motion position node of the target object when the motion distance is greater than the target distance interval or the motion time is greater than the target time interval;

[0249] The motion position node continuous determination grandchild unit is configured to continue to select the next temporary position node of the target object along the motion trajectory of the target object to determine the next motion position node of the target object.

[0250] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the target trajectory point determination unit may further include:

[0251] The adjacent road determination subunit is configured to determine the adjacent road closest to the motion trajectory point according to the positional relationship between the motion trajectory point and the existing roads on the map;

[0252] The target trajectory point determination subunit is configured to determine the motion trajectory point as the target trajectory point corresponding to the suspected missing road when the distance between the motion trajectory point and the adjacent road is greater than the target road distance.

[0253] In some exemplary embodiments of the present disclosure, based on the above exemplary embodiments, the point cluster determination module 1610 may further include:

[0254] The speed and error acquisition unit is configured to acquire the motion speed and positioning error of each of the motion trajectory points;

[0255] The noise trajectory point marking unit is configured to mark the motion trajectory points with a motion speed less than the speed limit or a positioning error greater than the error limit as noise trajectory points;

[0256] A noise trajectory point clearing unit, configured to clear the noise trajectory points among the movement trajectory points.

[0257] The specific details of the device for determining missing roads in the map in each of the above exemplary embodiments have been described in detail in the corresponding method for determining missing roads in the map, and thus will not be elaborated herein.

[0258] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0259] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-described method for determining missing roads in the map of the present disclosure can be implemented. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program code; the program product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network; when the program product runs on a computing device (which can be a personal computer, a server, a terminal device, a network device, etc.), the program code is used to cause the computing device to execute the method steps in the above-described exemplary embodiments of the present disclosure.

[0260] See Figure 17 As shown, a program product 1700 for implementing the above method according to an embodiment of the present disclosure may adopt a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a computing device (such as a personal computer, a server, a terminal device, a network device, etc.). However, the program product of the present disclosure is not limited thereto. In this exemplary embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0261] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium.

[0262] A readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0263] A readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0264] The program code contained on the readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the above.

[0265] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the C language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network (including a local area network (LAN) or a wide area network (WAN), etc.); or, it may be connected to an external computing device, for example, by connecting through the Internet using an Internet service provider.

[0266] In an exemplary embodiment of the present disclosure, an electronic device is further provided. The electronic device includes at least one processor and at least one memory for storing executable instructions of the processor; wherein, the processor is configured to execute the method steps in the above exemplary embodiments of the present disclosure by executing the executable instructions.

[0267] The following is combined with Figure 18The electronic device 1800 in this exemplary embodiment will be described. The electronic device 1800 is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0268] Refer to Figure 18 As shown, the electronic device 1800 is presented in the form of a general-purpose computing device. The components of the electronic device 1800 may include, but are not limited to: at least one processing unit 1810, at least one storage unit 1820, a bus 1830 connecting different system components (including the processing unit 1810 and the storage unit 1820), and a display unit 1840.

[0269] Among them, the storage unit 1820 stores program codes, and the program codes can be executed by the processing unit 1810, so that the processing unit 1810 executes the method steps in the above various exemplary embodiments of the present disclosure.

[0270] The storage unit 1820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit 1821 (RAM) and / or a cache storage unit 1822, and may further include a read-only storage unit 1823 (ROM).

[0271] The storage unit 1820 may further include a program / utility 1824 having a set (at least one) of program modules 1825. Such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0272] The bus 1830 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area bus using any bus structure in various bus structures.

[0273] The electronic device 1800 can also communicate with one or more external devices 1900 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 1800, and / or communicate with any device that enables the electronic device 1800 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 1850. And, the electronic device 1800 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1860. As Figure 18As shown, network adapter 1860 can communicate with other modules of electronic device 1800 via bus 1830. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with electronic device 1800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0274] Those skilled in the art will appreciate that various aspects of the present disclosure can be implemented as a system, method, or program product. Accordingly, various aspects of the present disclosure may be embodied in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which may be collectively referred to herein as "circuitry", "module", or "system".

[0275] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

[0276] The features, structures, or characteristics described above may be combined in any suitable manner in one or more embodiments, and where possible, the features discussed in the various embodiments are interchangeable. In the above description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, materials, etc. may be used. In other cases, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

Claims

1. A method for determining missing roads on a map, characterized in that, the method includes: determining a cluster of trajectory points corresponding to a suspected missing road, which consists of multiple moving trajectory points; obtaining the movement position information and movement direction information of each of the moving trajectory points in the cluster of trajectory points; determining the road confidence level that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information; determining the road confidence level that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information, including: determining the dispersion degree of the cluster of trajectory points for representing the position dispersion degree between each of the moving trajectory points according to the movement position information; determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the moving trajectory points according to the movement direction information; determining the road confidence level that the suspected missing road is a missing road on the map according to the dispersion degree and the disorder degree; determining the dispersion degree of the cluster of trajectory points for representing the position dispersion degree between each of the moving trajectory points according to the movement position information, including: determining the position distance between each of the moving trajectory points and each other moving trajectory point according to the movement position information of each of the moving trajectory points; determining the trajectory point dispersion degree of each of the moving trajectory points in the cluster of trajectory points according to the position distance; determining the dispersion degree of the cluster of trajectory points for representing the position dispersion degree between each of the moving trajectory points according to the trajectory point dispersion degree of the moving trajectory points; determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the moving trajectory points according to the movement direction information, including: determining a plurality of direction intervals corresponding to different direction ranges; dividing each of the moving trajectory points in the cluster of trajectory points into the direction intervals according to the movement direction information; determining the quantity ratio between the moving trajectory points in each direction interval and all the moving trajectory points in the cluster of trajectory points according to the division result of the direction intervals; determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the moving trajectory points according to the quantity ratio.

2. The method for determining missing roads on a map according to claim 1, characterized in that, determining a plurality of direction intervals corresponding to different direction ranges, including: determining a direction range covering all movement directions on the map plane; dividing the direction range into a plurality of direction intervals with the same range size.

3. The method for determining missing roads on a map according to claim 1, characterized in that, determining the road confidence level that the suspected missing road is a missing road on the map according to the dispersion degree and the disorder degree, including: respectively performing normalization processing on the dispersion degree and the disorder degree to obtain a normalized dispersion degree and a normalized disorder degree; determining the road confidence level that the suspected missing road is a missing road on the map according to the normalized dispersion degree and the normalized disorder degree.

4. The method for determining missing roads on a map according to any one of claims 1-3, characterized in that, Determine a cluster of trajectory points corresponding to a suspected missing road, which consists of multiple motion trajectory points, including: Obtain the motion trajectory information of the target object, and determine the motion trajectory points of the target object on the map according to the motion trajectory information; Screen the motion trajectory points according to the positional relationship between the motion trajectory points and the existing roads on the map to obtain target trajectory points corresponding to the suspected missing road; Determine the connectability between each of the target trajectory points and adjacent target trajectory points according to the distribution density of the target trajectory points; Connect multiple connectable target trajectory points to form a cluster of trajectory points corresponding to the suspected missing road.

5. The method for determining a missing road on a map according to claim 4, characterized in that, Obtaining the motion trajectory information of the target object includes: Obtain the motion trajectory information of the target object within the target map range and within the target time range.

6. The method for determining a missing road on a map according to claim 4, characterized in that, Determining the motion trajectory points of the target object on the map according to the motion trajectory information includes: Determine the initial position of the target object on the map according to the motion trajectory information, and use the initial position as the first motion position node of the target object; Starting from the initial position, sequentially select multiple motion position nodes of the target object along the motion trajectory of the target object, and determine the motion position nodes as the motion trajectory points of the target object on the map.

7. The method for determining a missing road on a map according to claim 6, characterized in that, Sequentially selecting multiple motion position nodes of the target object along the motion trajectory of the target object includes: Select a temporary position node of the target object along the motion trajectory of the target object; Obtain the motion distance and motion time between the temporary position node and the previous motion position node of the target object; when the motion distance is greater than the target distance interval or the motion time is greater than the target time interval, determine the temporary position node as the motion position node of the target object; Continue to select the next temporary position node of the target object along the motion trajectory of the target object to determine the next motion position node of the target object.

8. The method for determining a missing road on a map according to claim 4, characterized in that, Screening the motion trajectory points according to the positional relationship between the trajectory points and the existing roads on the map to obtain target trajectory points corresponding to the suspected missing road includes: Determine the nearest adjacent road to the motion trajectory point according to the positional relationship between the motion trajectory point and the existing roads on the map; When the distance between the motion trajectory point and the adjacent road is greater than the target road distance, determine the motion trajectory point as the target trajectory point corresponding to the suspected missing road.

9. The method for determining a missing road on a map according to claim 4, characterized in that, Before screening the movement trajectory points according to the positional relationship between the movement trajectory points and the existing roads on the map to obtain target trajectory points corresponding to suspected missing roads, the method further includes: Obtaining the movement speed and positioning error of each of the movement trajectory points; Marking the movement trajectory points with a movement speed less than the speed limit or a positioning error greater than the error limit as noise trajectory points; Clearing the noise trajectory points from the movement trajectory points.

10. An apparatus for determining missing roads on a map, Characterized in that The apparatus includes: A point cluster determination module configured to determine a cluster of trajectory points corresponding to a suspected missing road composed of a plurality of movement trajectory points; an information acquisition module configured to acquire the movement position information and movement direction information of each of the movement trajectory points in the cluster of trajectory points; A confidence determination module configured to determine the road confidence that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information; Determining the road confidence that the suspected missing road is a missing road on the map according to the movement position information and the movement direction information includes: Determining the dispersion degree of the cluster of trajectory points for representing the positional dispersion degree between each of the movement trajectory points according to the movement position information; Determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the movement trajectory points according to the movement direction information; Determining the road confidence that the suspected missing road is a missing road on the map according to the dispersion degree and the disorder degree; Determining the dispersion degree of the cluster of trajectory points for representing the positional dispersion degree between each of the movement trajectory points according to the movement position information includes: Determining the positional distance between each of the movement trajectory points and each of the other movement trajectory points according to the movement position information of each of the movement trajectory points; Determining the trajectory point dispersion degree of each of the movement trajectory points in the cluster of trajectory points according to the positional distance; Determining the dispersion degree of the cluster of trajectory points for representing the positional dispersion degree between each of the movement trajectory points according to the trajectory point dispersion degree of the movement trajectory points; Determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the movement trajectory points according to the movement direction information includes: Determining a plurality of direction intervals corresponding to different direction ranges; Dividing each of the movement trajectory points in the cluster of trajectory points into the direction intervals according to the movement direction information; determining the quantity ratio between the movement trajectory points in each of the direction intervals and all the movement trajectory points in the cluster of trajectory points according to the division result of the direction intervals; Determining the disorder degree of the cluster of trajectory points for representing the direction disorder degree of each of the movement trajectory points according to the quantity ratio.

11. A computer-readable storage medium, on which a computer program is stored, Characterized in that When the computer program is executed by a processor, it implements the method for determining missing roads on a map according to any one of claims 1-9.

12. An electronic device, Characterized in that Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the method for determining missing roads in a map according to any one of claims 1-9 by executing the executable instructions.

Images