Data processing method and computer readable medium

Abstract

The embodiment of the application provides a data processing method and a computer readable medium, wherein the data processing method comprises the following steps: determining a target road located around a target interest point from preset road network topology data based on the geographical position of the target interest point, wherein there is no other road between the target road and the target interest point; determining a road network topology scene type based on at least a road topology relationship corresponding to the target road; determining a candidate arrival point of the target interest point on the target road based on an arrival point selection rule corresponding to the road network topology scene type; obtaining more than one target trajectory point related to the target interest point from navigation trajectory data; and determining an arrival point corresponding to the target interest point according to the candidate arrival point and the target trajectory point. The embodiment of the application can improve the accuracy of the arrival point determination.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, and particularly, to a data processing method and a computer readable medium. BACKGROUND

[0002] In a geographic information system, a POI (Point Of Interest) represents a position point in the real world that is meaningful to a traveling object, which can be a building, a shop, a bus stop, or a scenic spot, etc. A reaching point corresponding to a POI refers to a position point that can be selected as a terminal point of a navigation route when the traveling object plans a navigation route from a starting point to the POI by using a navigation application software. It can be seen that the convenience and accuracy of the reaching point are crucial to the use experience of the navigation application software.

[0003] The related art discloses that a reaching point corresponding to a POI is mined by using a machine learning model. Since the machine learning model usually contains the nesting of multiple models, when the mined reaching point is inaccurate, it is difficult to locate the problem causing the inaccuracy of the mined reaching point and solve it. It can be seen that the mined reaching point by using the machine learning model has the problem that the mining process is difficult to optimize. Therefore, it is a problem to be solved by those skilled in the art to provide a technical solution that can optimize the mining process and guarantee the accuracy of the mined reaching point. SUMMARY

[0004] The purpose of the present application is to provide a data processing scheme to at least partially solve the above problems.

[0005] According to a first aspect of embodiments of the present application, a data processing method is provided, comprising: determining a target road located around a target POI from preset road network topology data based on a geographic position of the target POI; determining a road network topology scene type based on at least a road topology relationship corresponding to the target road; determining a candidate reaching point of the target POI on the target road based on a reaching point selection rule corresponding to the road network topology scene type; obtaining more than one target trajectory point related to the target POI from trajectory data; and determining a reaching point corresponding to the target POI according to the candidate reaching point and the target trajectory point.

[0006] According to a second aspect of the embodiments of the present application, a data processing apparatus is provided, comprising: a road determination module configured to determine a target road located around a target point of interest based on a geographic location of the target point of interest from preset road network topology data, wherein the target road and the target point of interest do not have other roads therebetween; a road network topology scene determination module configured to determine a road network topology scene type based on a road topology relationship corresponding to the target road; a candidate arrival point determination module configured to determine a candidate arrival point of the target point of interest on the target road based on an arrival point selection rule corresponding to the road network topology scene type; a target trajectory point determination module configured to obtain one or more target trajectory points related to the target point of interest from trajectory data; and an arrival point determination module configured to determine an arrival point corresponding to the target point of interest according to the candidate arrival point and the target trajectory point.

[0007] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is configured to store at least one executable instruction, and the executable instruction causes the processor to execute the data processing method of the first aspect of the above-mentioned embodiments.

[0008] According to a fourth aspect of the embodiments of the present application, a computer readable medium is provided, and the computer readable medium stores a computer program, and the computer program is executed by a processor to implement the data processing method of the first aspect of the above-mentioned embodiments.

[0009] The data processing method provided by the embodiments of the present application can determine the corresponding road network topology scene type according to the target road around the target point of interest, and then determine the candidate arrival point corresponding to the target point of interest on the target road based on the arrival point selection rule corresponding to the road network topology scene type, and combine the target trajectory point related to the target point of interest in the trajectory data of the travel object to determine a more accurate arrival point corresponding to the target point of interest. On the one hand, the determination of the arrival point considers the candidate arrival point and the target trajectory point, and the candidate arrival point is more objective and closer to the actual POI, thereby reducing the interference of the travel object behavior and improving the accuracy of the determination of the arrival point. On the other hand, the process of determining the arrival point is more simple and controllable. Moreover, the trajectory data in the cruising state after the navigation is ended is also closer to the actual navigation end position of the travel object, and therefore, the combination of the target trajectory point related to the target point of interest in the trajectory data to determine the arrival point further improves the accuracy of the determined arrival point. It can be seen that the scheme of the embodiments of the present application provides an optimized scheme which can effectively mine the arrival point, and the accuracy of the mined arrival point can be greatly improved through the scheme. BRIEF DESCRIPTION OF DRAWINGS

[0010] Other features, objects, and advantages of the application will become more apparent from the following detailed description when read in connection with the following drawings:

[0011] Figure 1 A flow chart of a data processing method in an embodiment of the application;

[0012] Figure 2 Another flow chart of a data processing method in an embodiment of the application;

[0013] Figure 3 A schematic diagram of a road network topology scenario in an embodiment of the application;

[0014] Figure 4 A schematic diagram of an application scenario of a data processing method in an embodiment of the application;

[0015] Figure 5 A schematic diagram of a structure of a data processing apparatus in an embodiment of the application;

[0016] Figure 6 A schematic diagram of a structure of an electronic device in an embodiment of the application. DETAILED DESCRIPTION

[0017] The application will be further described below in connection with the drawings and embodiments. It can be understood that the specific embodiments described herein are merely configured to explain the related application, but not to limit the application. In addition, it should be noted that, for the convenience of description, only the parts related to the application are shown in the drawings.

[0018] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0019] Currently, navigation application software is increasingly used, which provides convenience for travel. In the navigation process of a travel object through the navigation application software, corresponding navigation data can be generated. Since the navigation data contains travel object behavior data (such as the travel trajectory of the travel object), the POI corresponding arrival point can be mined based on the navigation data. In the related technology, clustering can be performed based on the navigation end point of the travel object, to obtain various clusters, and the clusters are compared to select the first-ranked cluster center as the arrival point. However, due to the large noise of the travel object behavior, the accuracy of the mined arrival point is low. For example, the positioning points in the travel trajectory of the travel object can be scattered or too concentrated, which cannot guarantee to form a good cluster. For another example, if the travel object terminates the navigation behavior in advance, the generated cluster center is usually not the accurate arrival point.

[0020] In addition, after clustering the navigation end points of the travel objects, the attributes of each cluster can be input into the ranking model as features, and other travel object behavior models can be combined to score and make decisions. However, in the case of using multiple models, if a problem is found, it is difficult to locate the specific cause, resulting in low accuracy in mining the arrival points through the model. To solve the above problems, the embodiment of the present application provides a data processing scheme to improve the accuracy of mining the arrival points.

[0021] With reference to Figure 1 , Figure 1 A flowchart of the data processing method in the embodiment of the present application can include the following steps:

[0022] In step S110, based on the geographic location of the target interest point, a target road located around the target interest point is determined from the preset road network topology data.

[0023] In the embodiment of the present application, the target interest point can be any interest point that the travel object wants to go to. The application software with map navigation capability (such as map navigation application software, online car-hailing application software, and life service application software) can display the location coordinates of the target interest point. After the travel object determines the target interest point, the application software with map navigation capability can recommend a navigation route for the user according to the starting location of the travel object and the location of the target interest point. The travel object starts navigation after selecting the navigation route.

[0024] The road network topology data describes the road network in the form of a topological structure, which contains the positions of roads, POIs, and other geographic elements and the information about the relationships between them. In the embodiment, after the travel object determines the target interest point, the geographic location of the target interest point can be combined with the road network topology data to determine the target road around the target interest point. The target road and the target interest point do not have other roads between them, that is, the target road is a road that does not have other roads between it and the target interest point.

[0025] In step S120, at least based on the road topology relationship corresponding to the target road, a road network topology scene type is determined.

[0026] In this embodiment, multiple road network topology scene types can be pre-established, with different types corresponding to different road network topology scenes. A road network topology scene can at least indicate the road and intersection conditions within that scene. Optionally, the road network topology scene may also include information about points of interest (PO), their corresponding target roads, and their corresponding candidate destinations, as well as their positional relationships. The road and intersection conditions differ under different road network topology scene types; for example, some scenes have intersections, while others do not; some scenes have parallel roads, while others do not, and so on. When the road network topology scene also includes information about PO, their corresponding target roads, and their corresponding candidate destinations, as well as their positional relationships, the number of target roads corresponding to PO can differ, the number of candidate destinations corresponding to PO can also differ, and the positional relationships between PO, target roads, and candidate destinations can also differ.

[0027] After identifying the target roads around the target point of interest, the road network topology scenario type can be determined based on the road topology relationships corresponding to the identified target roads.

[0028] An exemplary road network topology scenario type is as follows: Figure 3 As shown, it includes 5 types of road network topology scenarios. Figure 3 In the diagram, dots represent target points of interest, and lines represent target roads. The five possible scenarios for target roads surrounding a target point of interest are as follows: Figure 3 As shown in the image.

[0029] It should be noted that the road network topology scene type can also be determined solely based on the topological relationships between target roads. In one example, the road network topology scene type can be determined based on the road topology relationships of the target roads. For instance, if there is only one target road, it is the first type (i.e., the type corresponding to intersection 0 parallel to road 0); as another example, if there are two target roads, and the two target roads are parallel, it is the third type (i.e., the type corresponding to intersection 0 parallel to road 1), and so on. Of course, the road network topology scene type can also be determined by comprehensively considering points of interest and target roads.

[0030] Step S130: Based on the arrival point selection rules corresponding to the road network topology scene type, determine the candidate arrival points of the target point of interest on the target road.

[0031] In this embodiment, each road network topology scene type corresponds to a specific arrival point selection rule. This rule describes the positional relationship between roads, points of interest, and candidate arrival points in each road network topology scene type. The arrival point selection rule can be preset, thus allowing candidate arrival points to be obtained directly based on the road network topology scene type.

[0032] In an implementation, the number of candidate arrival points corresponding to the interest point can be less than a number threshold (e.g., 6, 8, etc.) in different road network topology scenario types, and the application does not limit the specific value of the number threshold. In this way, the arrival point corresponding to the target interest point can be selected from the limited candidate arrival points, and the efficiency of determining the arrival point can be improved.

[0033] For the target interest point, the candidate arrival point corresponding to the target interest point can be determined directly according to the road network topology scenario type in the case of determining the road network topology scenario type. It can be seen that the position of the candidate arrival point is also determined in the application, that is, the candidate arrival point can be determined in a static selection manner, rather than being determined according to the navigation trajectory data. In this way, the determination of the candidate arrival point can not be affected by the navigation trajectory data, and the candidate arrival point can be accurately determined even if the navigation trajectory data changes.

[0034] In step S140, one or more target trajectory points related to the target interest point are obtained from the trajectory data.

[0035] The trajectory data includes a series of trajectory points. In the embodiment of the application, the trajectory data can be the navigation trajectory data of the travel object, which can include the navigation trajectory data from the navigation starting point to the navigation ending point. Optionally, the trajectory data in the cruising state after the navigation ends can also be included. Since the trajectory data in the cruising state is closer to the actual navigation ending position of the travel object, the target trajectory point with higher relevance to the target interest point can be selected.

[0036] It should be noted that in actual application, the execution of steps S103 and S104 can not be in a specific order, and can be executed in parallel.

[0037] In step S150, the arrival point corresponding to the target interest point is determined according to the candidate arrival point and the target trajectory point.

[0038] In the embodiment of the application, after the candidate arrival point and the target trajectory point are determined, the candidate arrival point can be analyzed according to the target trajectory point, and the arrival point corresponding to the target interest point can be selected from the candidate arrival point. In an optional implementation, the arrival point can be determined directly based on the distance between the target trajectory point and the candidate arrival point. Specifically, the number of target trajectory points within a preset range around each candidate arrival point can be determined, and each number can be compared. The candidate arrival point corresponding to the largest number is taken as the arrival point corresponding to the target interest point.

[0039] The data processing method of this application embodiment can determine the corresponding road network topology scene type based on the target roads surrounding the target point of interest (POI). Then, based on the arrival point selection rules corresponding to the road network topology scene type, candidate arrival points corresponding to the POI on the target roads can be determined. Combined with the target trajectory points related to the POI in the traveler's trajectory data, a more accurate arrival point corresponding to the POI can be determined. On one hand, the determination of the arrival point considers both candidate arrival points and target trajectory points. The candidate arrival points are more objective and closer to the actual POI, thereby reducing interference from the traveler's behavior and improving the accuracy of arrival point determination. On the other hand, the process of determining the arrival point is simpler and more controllable. Furthermore, the trajectory data in the cruise state after navigation ends is closer to the traveler's actual navigation end location. Therefore, combining the target trajectory points related to the POI in this trajectory data to determine the arrival point further improves the accuracy of the determined arrival point. It can be seen that the solution of this application embodiment provides an optimized scheme for effectively mining arrival points, which can greatly improve the accuracy of the mined arrival points.

[0040] See Figure 2 , Figure 2 This is another flowchart of the data processing method in the embodiments of this application, which may include the following steps:

[0041] Step S210: Based on the geographical location of the target point of interest, determine the target road located around the target point of interest from the preset road network topology data.

[0042] There are no other roads between the target road and the target point of interest.

[0043] As mentioned earlier, road network topology data contains information about the location of roads, points of interest (POIs), and other geographic features, as well as the relationships between them. In this embodiment, road network topology data can be obtained directly, or raw road network data can be obtained and the road network topology data can be derived based on the relationships between the geographic features in the raw road network data.

[0044] In cases where road network topology data is obtained from original road network data, the road segments in the original road network data can be segments cut to a preset length (e.g., 50 meters or 60 meters). For example, a road may contain multiple road segments, so multiple straight-connected road segments can be merged into one road. Furthermore, the merged road may contain intersections, so a road containing intersections can be broken into multiple roads, etc.

[0045] After obtaining the road network topology data, in a feasible manner, if the perpendicular line of the target interest point on any road does not intersect with other roads in the road network topology information, the road can be determined as the target road located around the target interest point. In this way, the target road can be accurately and quickly determined.

[0046] In step S220, the road network topology scene type is determined based on at least the road topology relationship corresponding to the target road.

[0047] It should be noted that before performing this step, a plurality of road network topology scene types can be established according to the road topology relationship between the target roads corresponding to the interest points in the road network topology data. Further optionally, a plurality of road network topology scene types can be established according to the road topology relationship between the interest points, the arrival points corresponding to the interest points, and the target roads corresponding to the interest points in the road network topology data. The road network topology scene types established based on the road topology relationship between the target roads can effectively distinguish the scene, and the road network topology scene after adding the interest points, the arrival points, and the topology relationship between them and the target roads can contain more rich scene information, and can also make subsequent data processing more portable.

[0048] For roads, in actual scenarios, the relationship between roads can be expressed as straight connection, intersection connection (including perpendicular connection and non-perpendicular connection), and parallel from a geometric point of view. Two roads with intersection connection relationship can form an intersection, and two roads with parallel relationship can form a parallel road, therefore, in a feasible manner, the number of intersections and the number of parallel roads corresponding to the target road can be determined based on the road topology relationship corresponding to the target road; the road network topology scene type is determined according to the number of intersections and the number of parallel roads. Wherein, the number of intersections and the number of parallel roads corresponding to the target road can be determined based on the road topology relationship corresponding to the target road, which can include: determining the number of parallel roads formed by any two target roads with parallel relationship in the target road, and the number of intersections formed by any two target roads with intersection relationship in the plurality of target roads based on the road topology relationship corresponding to the target road.

[0049] An example of a road network topology scene type is shown in Figure 3 , which includes five road network topology scene types. When the number of target roads is one, the number of intersections and the number of parallel roads are both zero, when the number of target roads is more (in this embodiment, the number related to "more" such as "multiple", "multiple types" and the like all mean two or more), the number of intersections and / or the number of parallel roads is greater than zero, as shown in Figure 3 . Figure 3In this way, the road network topology scene type can be determined based on the topological relationship between roads, or the topological relationship between the interest point and the target road, and the topological relationship between multiple target roads.

[0050] In addition, from Figure 3 It can be seen from the above that, in the pre-established road network topology scene type, the number of candidate arrival points is not greater than 5. Since the arrival points are usually located on the road, the candidate arrival points are also located on the road. Therefore, the application embodiment converts the candidate arrival point assignment problem into a multiple-choice question with limited options, and the multiple-choice question can correspond to a classification problem of machine learning, which is more suitable for solving the problem by algorithm. It should be noted that, since the road network topology scene type is relatively complex, in actual application, the road network topology scene type established is not limited to Figure 3 the type shown in the above. In addition, in addition to increasing more road network topology scene types, scenes not included in the above range can also be uniformly represented as other scene types for processing.

[0051] It should be noted that, in some scenarios, the interest point data and the target road data are two independent data, in which case, the corresponding road network topology scene can be determined according to the analysis of the geographical position of the interest point and the geographical position of the target road, or according to the pre-stored corresponding relationship between the interest point and the target road, and the road network topology scene type is established. In addition, the interest point data, the arrival point data and the target road data are also independent of each other, and the establishment of the road network topology scene type can also use a similar way.

[0052] In step S230, the candidate arrival point of the target interest point on the target road is determined based on the arrival point selection rule corresponding to the road network topology scene type.

[0053] It can be seen from Figure 3 that, in the case of determining the road network topology scene type, the position of the candidate arrival point corresponding to the target interest point is also determined. For example, for the road network topology scene type in which the number of road junctions is 2 and the number of parallel roads is 1, the number of candidate arrival points corresponding to the target interest point is 5. Moreover, the position of the candidate arrival point can also be roughly determined.

[0054] It should be noted that, in the application embodiment, the candidate arrival point can be a point on the road, or a road junction, that is, the road junction is also regarded as a kind of candidate arrival point.

[0055] In step S240, one or more target trajectory points related to the target interest point are obtained from the trajectory data.

[0056] In the embodiments of the present application, the target trajectory point is generally a trajectory point with higher relevance to the target interest point. In general, the closer the distance to the target interest point, the higher the relevance of the trajectory point to the target interest point. In an optional implementation, a trajectory point with a distance to the target interest point less than a preset distance threshold (for example, 80 meters or 100 meters, etc.) can be selected as the target trajectory point. The preset distance threshold can be appropriately set by those skilled in the art according to actual conditions. In addition, if the number of selected target trajectory points is large, a preset number of target trajectory points can be randomly selected. The size of the preset number can be adjusted according to different application scenarios, which is not limited herein. By setting an appropriate preset number, the interference of invalid noise can be excluded.

[0057] Optionally, the trajectory data includes trajectory data in a cruising state after the navigation of the travel object ends, so as to select a target trajectory point with higher relevance to the target interest point.

[0058] In step S250, a target road near the target trajectory point is determined according to the distance between the target trajectory point and the target road.

[0059] In the embodiments of the present application, after the target trajectory point and the candidate arrival point are determined, in a feasible manner, the candidate arrival point can be directly selected as the final arrival point corresponding to the target interest point according to the distance between the target trajectory point and the candidate arrival point. Although this method can also determine the arrival point, in order to make full use of the effective information obtained and obtain a more accurate arrival point corresponding to the target interest point, the candidate arrival point is selected in combination with the target road, and then the arrival point corresponding to the target interest point is determined.

[0060] Specifically, in the embodiments, the candidate target road near the target trajectory point can be determined according to the distance between the target trajectory point and the target road. The closer the distance between the target trajectory point and the target road, the closer the target trajectory point is to the target road. When the number of target roads is multiple, for a single target trajectory point, the projection distance between the target trajectory point and each target road is determined; from all the projection distances, the minimum projection distance and the second minimum projection distance are determined; if the minimum projection distance is less than a set distance threshold, and the difference between the second minimum projection distance and the minimum projection distance is greater than a difference threshold, the target road corresponding to the minimum projection distance is determined as the candidate target road near the target trajectory point. The specific settings of the distance threshold and the difference threshold can be appropriately set by those skilled in the art according to actual needs, for example, the distance threshold can be 30 meters, 50 meters, etc., and the difference threshold can be 10 meters, 20 meters, etc., which are not limited by the present application. By comprehensively considering the minimum projection distance, the second minimum projection distance, and the relationship between them and the respective corresponding thresholds, a more accurate candidate target road can be obtained.

[0061] Of course, in another possible implementation, after the minimum projection distance is determined, the target road corresponding to the minimum projection distance can also be directly determined as a candidate target road adjacent to the target trajectory point, and the like. In addition, when the number of target roads is one, the target road can be directly determined as a candidate target road adjacent to the target trajectory point.

[0062] After the above operations are performed for each target trajectory point, the candidate target road can be effectively determined from the plurality of target roads.

[0063] In step S260, the preferred target road is determined from the candidate target roads according to the total number of target trajectory points corresponding to the candidate target roads.

[0064] In the embodiments of the present application, if the candidate target roads determined through step S250 include multiple candidate target roads, the number of target trajectory points corresponding to the multiple candidate target roads can be determined based on the number of target trajectory points corresponding to each candidate target road, and the maximum number and the second maximum number are determined from the number of target trajectory points. If the maximum number is greater than a preset multiple of the second maximum number, the candidate target road corresponding to the maximum number is determined as the preferred target road. The specific setting of the preset multiple can be appropriately set by those skilled in the art according to actual needs.

[0065] For example, the number of target trajectory points corresponding to the candidate target road one is the maximum, such as 50, and the number of target trajectory points corresponding to the candidate target road two is the second maximum, such as 20, and when the preset multiple is 2, the candidate target road one can be determined as the preferred target road. However, it is not limited thereto, and the candidate target road corresponding to the maximum number can also be directly determined as the preferred target road, and the like, which is not limited in the present application.

[0066] In step S270, the arrival point corresponding to the target interest point is determined according to the candidate arrival points on the preferred target road.

[0067] As described above, since the arrival point is usually located on the road (including the intersection), after the preferred target road is determined, the arrival point corresponding to the target interest point can be selected from the candidate arrival points on the preferred target road. For example, the candidate arrival point closest to the target interest point can be directly determined as the arrival point corresponding to the target interest point. Alternatively, if the candidate arrival points are relatively close to a certain intersection, the intersection on the preferred target road can also be determined as the arrival point corresponding to the target interest point.

[0068] The data processing method of the embodiments of the present application can determine the corresponding road network topology scene type according to the target road around the target point of interest; then, based on the arrival point selection rule corresponding to the road network topology scene type, the candidate arrival point corresponding to the target point of interest on the target road can be determined, and in combination with the target trajectory point related to the target point of interest in the trajectory data of the travel object, a more accurate arrival point corresponding to the target point of interest can be determined. On the one hand, the determination of the arrival point takes into account the candidate arrival point and the target trajectory point, and the candidate arrival point is more objective and closer to the actual POI, thereby reducing the interference of the travel object behavior and improving the accuracy of the determination of the arrival point. On the other hand, the process of determining the arrival point is more simple and controllable. Moreover, the trajectory data in the cruising state after the end of navigation is also closer to the actual navigation end position of the travel object, and therefore, in combination with the target trajectory point related to the target point of interest in the trajectory data, the accuracy of the determined arrival point is further improved. It can be seen that, through the scheme of the embodiments of the present application, an optimized scheme for effectively mining the arrival point is provided, and the accuracy of the mined arrival point can be greatly improved.

[0069] The data processing method provided by the embodiments of the present application can be executed by any appropriate device with data processing capability, including but not limited to: a camera, a terminal, a mobile terminal, a PC, a server, a vehicle-mounted device, an entertainment device, an advertising device, a personal digital assistant (PDA), a tablet computer, a notebook computer, a palm game console, glasses, a watch, a wearable device, a virtual display device or a display enhancement device, etc.

[0070] Referring to Figure 4 , Figure 4 is a schematic diagram of an application scenario of the data processing method in the embodiments of the present application, and the above process will be exemplarily described in combination with Figure 4 a specific scenario.

[0071] Suppose that the target point of interest is a coffee shop, and the coffee shop is located at the corner of road A and road B. Based on the road network topology data, if the distance between the coffee shop and other roads is far (for example, greater than 100 meters, etc.), the target road around the coffee shop can be determined as road A and road B. According to the position relationship between the coffee shop and road A and road B, it can be determined that the road network topology scene type corresponding to the coffee shop belongs to the second scene type shown in Figure 3 , that is, the scene type with one intersection and 0 parallel roads. Based on the road network topology scene type corresponding to the coffee shop, the number of candidate arrival points corresponding to the coffee shop can be determined as 3, and the positions of the candidate arrival points are as shown in the positions of the candidate arrival points in the second scene type in Figure 3 .

[0072] In addition, based on the trajectory data of the travel object, a target trajectory point can be determined, which has a distance between the trajectory data and the coffee shop less than a preset distance threshold. It is assumed that 50 target trajectory points can be obtained.

[0073] Subsequently, a candidate arrival point corresponding to the coffee shop can be determined based on the candidate arrival point and the target trajectory point. Specifically, distances between the 50 target trajectory points and the road A and the road B can be calculated, and a relationship between the target trajectory points and the road A or the road B can be established according to the distances. If the number of target trajectory points corresponding to the road A is 38 and the number of target trajectory points corresponding to the road B is 12, and the number of target trajectory points corresponding to the road A is greater than twice the number of target trajectory points corresponding to the road B, the road A can be determined as the preferred target road. Finally, a candidate arrival point on the road A can be selected as the arrival point corresponding to the coffee shop. For example, a candidate arrival point closest to the coffee shop on the road A can be selected as the arrival point corresponding to the coffee shop. Thus, the arrival point corresponding to the coffee shop is obtained.

[0074] It can be seen that the data processing method of the present application determines the candidate arrival point based on the network topology scene type, and does not need to analyze the trajectory points in the navigation trajectory data of the travel object to determine the candidate arrival point, which can reduce the interference of the travel object behavior and improve the accuracy of the determined candidate arrival point. Moreover, the process of determining the candidate arrival point is more simple and controllable. In the determination of the arrival point corresponding to the target interest point based on the candidate arrival point and the target trajectory point, the target road is combined, and the relationship between the target trajectory point and the target road is combined, and the arrival point corresponding to the target interest point is selected from the candidate arrival points on the preferred target road, which can improve the accuracy of the arrival point determination.

[0075] Reference Figure 5 , Figure 5 FIG. 1 is a schematic diagram of a data processing device according to an embodiment of the present application. As shown in FIG. 1, the data processing device includes a processor 500 and a memory 500. The memory 500 stores a computer program. The processor 500 is configured to execute the computer program stored in the memory 500.

[0076] The road determination module 510 is configured to determine a target road located around the target interest point from the preset road network topology data based on the geographical position of the target interest point, and the target road does not have other roads between the target road and the target interest point. The road network topology scene determination module 520 is configured to determine a road network topology scene type based on at least a road topology relationship corresponding to the target road. The candidate arrival point determination module 530 is configured to determine a candidate arrival point of the target interest point on the target road based on an arrival point selection rule corresponding to the road network topology scene type. The target trajectory point determination module 540 is configured to obtain one or more target trajectory points related to the target interest point from the trajectory data. The arrival point determination module 550 is configured to determine an arrival point corresponding to the target interest point according to the candidate arrival point and the target trajectory point.

[0077] In an optional implementation, the reaching point determination module 550 comprises: an association relationship determination unit configured to determine a candidate target road near a target trajectory point according to a distance between the target trajectory point and a target road; a first preferred target road determination unit configured to determine a first preferred target road from the candidate target roads according to a total number of target trajectory points corresponding to the candidate target roads; and a reaching point determination unit configured to determine a reaching point corresponding to the target interest point according to a candidate reaching point on the first preferred target road.

[0078] In an optional implementation, the association relationship determination unit is specifically configured to determine, for each target trajectory point, a projection distance of the target trajectory point to each target road; determine a minimum projection distance and a second minimum projection distance from all the projection distances; and determine a target road corresponding to the minimum projection distance as a candidate target road near the target trajectory point if the minimum projection distance is smaller than a set distance threshold and a difference between the second minimum projection distance and the minimum projection distance is greater than a difference threshold.

[0079] In an optional implementation, the first preferred target road determination unit is configured to determine a number of target trajectory points corresponding to each candidate target road based on a number of target trajectory points corresponding to each candidate target road, and determine a maximum number and a second maximum number from the numbers of target trajectory points; and determine a candidate target road corresponding to the maximum number as the first preferred target road if the maximum number is greater than a preset multiple of the second maximum number.

[0080] In an optional implementation, the road network topology scenario determination module 520 is specifically configured to determine a number of intersections and a number of parallel roads corresponding to the target road based on a road topology relationship corresponding to the target road, and determine the road network topology scenario type according to the number of intersections and the number of parallel roads.

[0081] In an optional implementation, when determining the number of intersections and the number of parallel roads corresponding to the target road based on a road topology relationship corresponding to the target road, the road network topology scenario determination module 520 is configured to determine the number of parallel roads formed by any two target roads having a parallel relationship in the target road and the number of intersections formed by any two target roads having a crossing relationship in the target road based on the road topology relationship corresponding to the target road.

[0082] In an optional implementation, the data processing apparatus of the embodiment of the present application further comprises a road network topology scenario establishment module configured to establish a plurality of road network topology scenario types according to a road topology relationship between target roads corresponding to interest points in the road network topology data.

[0083] In an optional implementation, the road network topology scenario establishing module is specifically configured to establish multiple road network topology scenario types according to the road topology relationship among the interest point, the arrival point corresponding to the interest point, and the target road corresponding to the interest point in the road network topology data.

[0084] In an optional implementation, the road determining module 510 is specifically configured to determine a road as a target road located around a target interest point if, according to the geographic location of the target interest point, a perpendicular line of the target interest point on any road does not intersect with other roads in the preset road network topology data.

[0085] The data processing apparatus provided in this embodiment is used to implement the corresponding data processing method in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be described here again.

[0086] It should be noted that, according to the needs of implementation, each module / step described in the embodiments of the present application can be split into more modules / steps, or two or more modules / steps or part of the operations of the modules / steps can be combined into a new module / step, to achieve the purpose of the embodiments of the present application.

[0087] Figure 6 The electronic device in this embodiment is a schematic structural diagram of an electronic device, which can include a processor 602, a communication interface 604, a memory 606, and a communication bus 608.

[0088] The processor 602, the communication interface 604, and the memory 606 can communicate with each other through the communication bus 608.

[0089] The communication interface 604 is configured to communicate with other electronic devices or servers.

[0090] The processor 602 is configured to execute the program 610, and specifically can execute the related steps in the foregoing data processing method embodiments.

[0091] Specifically, the program 610 can include program code, and the program code includes computer operation instructions.

[0092] The processor 602 can be a central processing unit CPU, or an application specific integrated circuit ASIC, or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device can be processors of the same type, such as one or more CPUs; or can be processors of different types, such as one or more CPUs and one or more ASICs.

[0093] The memory 606 is configured to store a program 610. The memory 606 can include a high-speed RAM memory, and can further include a non-volatile memory such as at least one disk memory.

[0094] The program 610 can be specifically configured to enable the processor 602 to perform the corresponding steps in the above-described data processing method embodiments.

[0095] The specific implementation of each step in the program 610 can refer to the corresponding description in the above-described data processing method embodiments, and will not be described here. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working process of the above-described device and module can refer to the corresponding process description in the foregoing method embodiments, and will not be described here.

[0096] As another aspect, the present application also provides a computer readable medium, which can be included in the apparatus described in the above embodiments, or can exist independently without being assembled into the apparatus. The above computer readable medium carries one or more programs, which, when executed, implement the above data processing method.

[0097] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code configured to perform the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication part, and / or installed from a detachable medium. When the computer program is executed by a central processing unit, the above functions defined in the method of the present application are performed.

[0098] It should be noted that the computer readable medium in the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable medium may, for example, but not limited to, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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 medium, a magnetic storage medium, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take on various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium that can send, propagate or transmit the program for use by or in connection with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.

[0099] The expressions "first", "second", "the first" or "the second" used in various embodiments of the present application can modify various components regardless of order and / or importance, but these expressions do not limit the corresponding components. The above expressions are only configured for the purpose of distinguishing the elements from other elements. For example, the first user equipment and the second user equipment represent different user equipment, although both are user equipment. For example, without departing from the scope of the present disclosure, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element.

[0100] The above description is only the preferred embodiment of the present application and the explanation of the technical principles applied. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with each other to form technical solutions with similar functions disclosed in the present application (but not limited to).

Claims

1. A data processing method, comprising: determining, based on a geographical position of a target point of interest, a target road located around the target point of interest from preset road network topology data, the target road having no other road between the target road and the target point of interest; determining a road network topology scene type based on at least a road topology relationship corresponding to the target road; determining a candidate arrival point of the target point of interest on the target road based on an arrival point selection rule corresponding to the road network topology scene type; obtaining more than one target trajectory point related to the target point of interest from trajectory data; determining an arrival point corresponding to the target point of interest according to the candidate arrival point and the target trajectory point.

2. The method of claim 1, wherein, The determining of the arrival point corresponding to the target point of interest according to the candidate arrival point and the target trajectory point comprises: determining a candidate target road adjacent to the target trajectory point according to a distance between the target trajectory point and the target road; determining a preferred target road from the candidate target roads according to a total number of target trajectory points corresponding to the candidate target road; determining the arrival point corresponding to the target point of interest according to the candidate arrival point on the preferred target road.

3. The method of claim 2, wherein, The determining of the candidate target road adjacent to the target trajectory point according to the distance between the target trajectory point and the target road comprises: determining, for each target trajectory point, a projection distance of the target trajectory point to each target road; determining a minimum projection distance and a second minimum projection distance from all projection distances; if the minimum projection distance is smaller than a set distance threshold and a difference between the second minimum projection distance and the minimum projection distance is greater than a difference threshold, determining the target road corresponding to the minimum projection distance as the candidate target road adjacent to the target trajectory point.

4. The method of claim 2 or 3, wherein, The determining of the preferred target road from the candidate target roads according to the total number of target trajectory points corresponding to the candidate target road comprises: determining a number of target trajectory points corresponding to a plurality of candidate target roads based on a number of target trajectory points corresponding to each candidate target road, and determining a maximum number and a second maximum number from the numbers of target trajectory points; if the maximum number is greater than a preset multiple of the second maximum number, determining the candidate target road corresponding to the maximum number as the preferred target road.

5. The method of any of claims 1-3, wherein, The determining of the road network topology scene type based on at least the road topology relationship corresponding to the target road comprises: determining a number of intersections and a number of parallel roads corresponding to the target road based on the road topology relationship corresponding to the target road; determining the road network topology scene type according to the number of intersections and the number of parallel roads.

6. The method of claim 5, wherein, The determining of the number of intersections and the number of parallel roads corresponding to the target road based on the road topology relationship corresponding to the target road comprises: determining the number of parallel roads formed by any two target roads having a parallel relationship in the target road and the number of intersections formed by any two target roads having a crossing relationship in the target road based on the road topology relationship corresponding to the target road.

7. The method of any one of claims 1-3, wherein, Before determining the road network topology scene type based on the road topology relationship of the target road, the method further comprises: According to the road topology relationship between the target roads corresponding to the interest points in the road network topology data, a plurality of road network topology scene types are established.

8. The method of claim 7, wherein, The step of establishing a plurality of road network topology scene types according to the road topology relationship between the target roads corresponding to the interest points in the road network topology data comprises: According to the road topology relationship between the interest points, the arrival points corresponding to the interest points and the target roads corresponding to the interest points in the road network topology data, a plurality of road network topology scene types are established.

9. The method of any of claims 1-3, wherein, The step of determining the target road located around the target interest point from the preset road network topology data based on the geographic location of the target interest point comprises: If according to the geographic location of the target interest point, it is determined that the perpendicular line of the target interest point on any road in the preset road network topology data does not cross other roads, the road is determined as the target road located around the target interest point. 10.A computer readable medium having stored thereon a computer program, which, when executed by a processor, implements the data processing method according to any one of claims 1-9.

Images