Entrance and exit marking and route planning method and device, medium and electronic equipment

Abstract

The specification discloses a method, device, medium and electronic equipment for entrance and exit labeling and route planning. In the method, at least one target historical order matched with each to-be-labeled AOI can be obtained. For each target historical order, a delivery track corresponding to the target historical order is determined. Then, an intersection point generated by the delivery track corresponding to the target historical order and the boundary of the to-be-labeled AOI is determined as the intersection point corresponding to the target historical order. According to the intersection points corresponding to the target historical orders, the entrance and exit of the to-be-labeled AOI are determined and labeled. Since the service platform can determine the entrance and exit of the to-be-labeled AOI from the intersection points of the delivery tracks and the boundary of the to-be-labeled AOI, the method can automatically determine the entrance and exit of the to-be-labeled AOI through historical data, thereby improving the delivery efficiency to a certain extent.

Description

Technical Field

[0001] This specification relates to the field of computers, and more particularly to a method, apparatus, readable storage medium, and electronic device for entrance / exit marking and route planning. Background Technology

[0002] As more and more people order goods online, delivery services are becoming increasingly widespread. Delivery personnel can deliver online orders to users, greatly facilitating their lives.

[0003] Delivery drivers need to deliver goods ordered online from merchants to customers. In practice, most customers' delivery locations are within their Area of ​​Interest (AOI), such as residential areas or hospitals. However, the AOI information displayed on electronic maps is not always accurate; for example, the AOI's entrances and exits may not be marked. This forces delivery drivers to contact customers again to determine the delivery route because they cannot locate the AOI's entrances and exits on the map, thus reducing delivery efficiency.

[0004] Therefore, determining the entrance and exit points of the user's AOI to improve delivery efficiency is an urgent problem to be solved. Summary of the Invention

[0005] This specification provides a method, apparatus, medium, and electronic device for entrance / exit marking and route planning, in order to partially solve the aforementioned problems existing in the prior art.

[0006] The following technical solution is adopted in this specification:

[0007] This manual provides a method for marking entrances and exits, including:

[0008] Identify the regions of interest (AOIs) to be labeled;

[0009] For each AOI to be labeled, obtain at least one target historical order that matches that AOI;

[0010] For each target historical order, determine the delivery trajectory that the delivery capacity executing the target historical order takes during the execution of the target historical order, and use it as the delivery trajectory corresponding to the target historical order;

[0011] Based on the delivery trajectory corresponding to the target historical order, determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, and use it as the intersection point corresponding to the target historical order;

[0012] Based on the intersection points corresponding to at least one target historical order, determine the entrance and exit points of the AOI to be labeled and label them.

[0013] Optionally, obtaining at least one target historical order matching each AOI to be labeled includes:

[0014] For each historical order, determine the delivery location of the corresponding shipment;

[0015] The AOI into which the delivery location falls is determined by using a preset AOI search tree;

[0016] This historical order is used as the target historical order that matches the AOI to which the delivery location falls.

[0017] Optionally, determining the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, based on the delivery trajectory corresponding to the target historical order, as the intersection point corresponding to the target historical order, includes:

[0018] The intersection point between the delivery trajectory corresponding to the target's historical order and the boundary of the AOI to be labeled on the preset electronic map is determined as the intersection point to be identified.

[0019] In the delivery trajectory corresponding to the target historical order, determine the trajectory point that is adjacent to the intersection point to be identified and located outside the boundary of the AOI to be labeled, as the first trajectory point; and determine the trajectory point that is adjacent to the intersection point to be identified and located inside the boundary of the AOI to be labeled, as the second trajectory point.

[0020] If, among the trajectory points included in the delivery trajectory corresponding to the target historical order, it is determined that there are no less than a first set number of continuous trajectory points adjacent to the first trajectory point outside the boundary of the AOI to be labeled, and no less than a second set number of continuous trajectory points adjacent to the second trajectory point inside the boundary of the AOI to be labeled, the intersection point to be identified is taken as the intersection point corresponding to the target historical order.

[0021] Optionally, determining and labeling the entrance / exit of the AOI to be labeled based on the intersection points corresponding to the at least one target historical order includes:

[0022] For each target historical order, if the intersection point corresponding to the target historical order is determined to meet the preset conditions, the intersection point corresponding to the target historical order is used as a candidate annotation point;

[0023] Based on the candidate annotation points, determine the entrance and exit of the AOI to be annotated and annotate it.

[0024] Optionally, for each target historical order, if the intersection point corresponding to the target historical order is determined to meet preset conditions, the intersection point corresponding to the target historical order is used as a candidate annotation point, including:

[0025] For each intersection point corresponding to the target historical order, determine the trajectory points adjacent to the intersection point in the delivery trajectory corresponding to the target historical order, and determine the line connecting the trajectory points adjacent to the intersection point and the intersection point;

[0026] If it is determined that the angle between the connecting line and the perpendicular line on the boundary of the AOI to be labeled, where the intersection point is located, is not greater than a set angle, then the intersection point is determined as a candidate labeling point that meets the preset conditions.

[0027] Optionally, for each target historical order, if the intersection point corresponding to the target historical order is determined to meet preset conditions, the intersection point corresponding to the target historical order is used as a candidate annotation point, including:

[0028] For each intersection point corresponding to the target historical order, if it is determined that the distance between the intersection point and the adjacent trajectory point does not exceed a set distance in the delivery trajectory corresponding to the target historical order, the intersection point is determined as a candidate annotation point that meets the preset conditions.

[0029] Optionally, determining and labeling the entrance / exit of the AOI to be labeled based on the candidate labeling points includes:

[0030] Each candidate annotation point is input into a preset screening model to determine the probability density distribution function used to characterize the probability density of each candidate annotation point;

[0031] Each peak is determined from the probability density distribution function;

[0032] For each peak, if it is determined that the peak value is not less than a set threshold, the candidate annotation point corresponding to the peak is used as the entrance / exit of the AOI to be annotated.

[0033] Optionally, before determining the delivery trajectory traversed by the delivery capacity executing the target historical order during the execution of the target historical order, as the delivery trajectory corresponding to the target historical order, the method further includes:

[0034] For each trajectory point in the delivery trajectory corresponding to the target historical order, if the distance between the trajectory point and its adjacent trajectory points is not less than a set distance, the trajectory point is removed from the delivery trajectory corresponding to the target historical order.

[0035] Optionally, before determining the delivery trajectory traversed by the delivery capacity executing the target historical order during the execution of the target historical order, as the delivery trajectory corresponding to the target historical order, the method further includes:

[0036] For each trajectory point in the delivery trajectory corresponding to the target historical order, if the delivery speed of the delivery capacity for the target historical order at that trajectory point is not less than the set speed, then that trajectory point is removed from the delivery trajectory corresponding to the target historical order.

[0037] This manual provides a route planning method, including:

[0038] Receive the user's target order;

[0039] Based on the delivery address of the target order, determine the AOI to which the target order belongs, and designate it as the target AOI;

[0040] Based on the entrances and exits marked in the target AOI, the delivery route of the target order is planned. The entrances and exits of the target AOI are marked using the aforementioned entrance and exit marking method.

[0041] The planned delivery routes are recommended to the delivery capacity that will fulfill the target order.

[0042] Optionally, the step of planning the delivery route for the target order based on the entrances and exits marked in the target AOI includes:

[0043] Based on the historical orders corresponding to the target AOI, select the target entrance / exit from each entrance / exit marked in the target AOI;

[0044] Based on the target entrance / exit, a delivery route is planned that passes through the target entrance / exit.

[0045] This specification provides a device for indicating entrances and exits, including:

[0046] The first determination module is configured to determine each region of interest (AOI) to be labeled.

[0047] The acquisition module is configured to acquire at least one target historical order that matches each AOI to be labeled.

[0048] The second determining module is configured to determine, for each target historical order, the delivery trajectory traversed by the delivery capacity executing the target historical order during the execution of the target historical order, and use it as the delivery trajectory corresponding to the target historical order.

[0049] The third determining module is configured to determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, based on the delivery trajectory corresponding to the target historical order, and use it as the intersection point corresponding to the target historical order;

[0050] The annotation module is configured to determine the entrance and exit of the AOI to be annotated based on the intersection points corresponding to the at least one target historical order and to annotate them.

[0051] This specification provides a route planning device, comprising:

[0052] A receiving module configured to receive user target orders;

[0053] The determination module is configured to determine the AOI to which the target order belongs based on the delivery address of the target order, and use it as the target AOI;

[0054] The planning module is configured to plan the delivery route of the target order based on the entrances and exits marked in the target AOI, wherein the entrances and exits of the target AOI are marked using the aforementioned entrance and exit marking method.

[0055] The recommendation module is configured to recommend planned delivery routes to delivery capacity that will execute the target order.

[0056] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for marking entrances and exits or the above-described method for route planning.

[0057] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for entrance / exit labeling or the above-described method for route planning.

[0058] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0059] As can be seen from the above method, the service platform can identify each Area of ​​Interest (AOI) to be labeled, and for each AOI, obtain at least one target historical order that matches it. For each target historical order, determine the delivery trajectory traversed by the delivery capacity executing the target historical order during its execution, which is then used as the delivery trajectory corresponding to that target historical order. Next, determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, which is then used as the intersection point corresponding to that target historical order. Based on the intersection point corresponding to at least one target historical order, determine and label the entrance and exit of the AOI to be labeled.

[0060] As can be seen from the above method, the service platform can determine and mark the entrance and exit of the AOI to be marked by analyzing the intersections of several historical delivery trajectories that have crossed the AOI. Therefore, this method can automatically determine the entrance and exit of the AOI to be marked using historical data, thereby improving delivery efficiency to some extent. Attached Figure Description

[0061] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and are used to explain this specification, but do not constitute an undue limitation thereof. In the drawings:

[0062] Figure 1 This is a flowchart illustrating one method for marking entrances and exits as described in this specification.

[0063] Figure 2 This is a schematic diagram of a region of interest (AOI) provided in this specification;

[0064] Figure 3 This is a schematic diagram of an AOI search tree provided in this specification;

[0065] Figure 4 This is a schematic diagram illustrating the delivery trajectory of a target historical order provided in this specification.

[0066] Figure 5 This is a schematic diagram of a noise point in a delivery trajectory provided in this specification;

[0067] Figure 6 This is a schematic diagram of the intersection of a delivery trajectory and the boundary of an AOI to be labeled, as provided in this specification.

[0068] Figure 7 This is a schematic diagram of a probability density distribution function provided in this specification;

[0069] Figure 8 This is a flowchart illustrating a route planning method provided in this specification.

[0070] Figure 9 This is a schematic diagram of an entrance / exit marking device provided in this specification;

[0071] Figure 10 A schematic diagram of a route planning device provided in this specification;

[0072] Figure 11 The corresponding information provided in this specification Figure 1 Or Figure 8 A schematic diagram of an electronic device. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0074] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0075] Figure 1 This is a flowchart illustrating one method for marking entrances and exits as described in this specification, specifically including the following steps:

[0076] S101: Determine the regions of interest (AOIs) to be labeled.

[0077] In practical applications, users of delivery services are mostly located within their Area of ​​Interest (AOI). The AOI is a region pre-defined on an electronic map by the service platform staff through data collection. AOIs can refer to communities such as hospitals, schools, residential areas, and office buildings. Therefore, when executing a delivery task, delivery vehicles must enter from the entrance / exit of the user's AOI to reach the user's specific location and deliver the goods. The delivery vehicles mentioned here can refer to delivery personnel, delivery robots, drones, unmanned vehicles, and other units with a certain transportation and carrying capacity, such as... Figure 2 As shown.

[0078] Figure 2 This is a schematic diagram of a region of interest (AOI) provided in this specification.

[0079] For example, such as Figure 2 As shown, a user who places an order sets their shipping address to... Figure 2 Building 1 of Community H (Community H refers to the Area of ​​Interest, AOI) where the user is located, has either a north or east entrance. Therefore, if a delivery vehicle receives an order from this user, it needs to enter through either the north or east entrance of the community to reach Building 1 and deliver the ordered item to the user.

[0080] Therefore, the service platform needs to pre-determine the Regions of Interest (AOIs) that require labeling of entrances and exits based on its actual business needs. These AOIs will then be labeled in the subsequent process. In this specification, AOIs to be labeled can be those with fewer than a certain number of entrances and exits. For example, if an AOI already has fewer than two labeled entrances and exits, then that AOI can be identified as an AOI to be labeled. AOIs with a large number of entrances and exits may not need to be labeled.

[0081] S102: For each AOI to be labeled, obtain at least one target historical order that matches the AOI to be labeled.

[0082] After identifying each AOI to be labeled, the service platform can obtain at least one target historical order that matches each AOI. Specifically, the service platform can identify historical orders whose delivery locations are within the AOI to be labeled, and use these as the target historical orders matching that AOI. The delivery location of these historical orders can refer to the delivery address set by the user for that historical order, or it can refer to the actual delivery location where the delivery capacity handled the delivery to the user when executing the historical order.

[0083] Specifically, for each historical order, the service platform can determine the delivery location of the corresponding item, and then, through a pre-defined AOI search tree, identify the AOI that the delivery location falls into, and designate that historical order as the target historical order matching that AOI. The AOI search tree mentioned here refers to a tree-like data structure that stores various AOIs or Points of Interest (POIs) within AOIs according to their geographical containment relationships, such as... Figure 3 As shown.

[0084] Figure 3 This is a schematic diagram of an AOI search tree provided in this specification.

[0085] In the example above, if community H is located in district B of city A, then the service platform can create such... Figure 3 The AOI search tree shows that, based on geographical containment, areas B and C are stored as child nodes of the node corresponding to city A, while areas H and G are stored as child nodes of the node corresponding to area B. Therefore, if the service platform obtains a historical order with a delivery location within area H, it can determine, based on the AOI search tree, that the historical order is a target historical order matching the AOI of area H.

[0086] S103: For each target historical order, determine the delivery trajectory that the delivery capacity used to execute the target historical order takes during the execution of the target historical order, and use it as the delivery trajectory corresponding to the target historical order.

[0087] After the service platform identifies at least one target historical order that matches the AOI to be labeled, it can determine the delivery trajectory of the delivery capacity that executes the target historical order during the execution of the target historical order, and use it as the delivery trajectory corresponding to the target historical order.

[0088] In practical applications, the service platform can collect real-time data on the trajectory points traversed by delivery vehicles during their delivery processes. This allows the platform to obtain the delivery trajectory of the delivery vehicle, formed by connecting these trajectory points. In addition to collecting data on each trajectory point, the platform also collects information such as the delivery vehicle's speed at each trajectory point.

[0089] Therefore, the service platform can determine the delivery trajectory of the delivery capacity executing the target historical order, and extract the portion of the delivery trajectory from entering the AOI to leaving the AOI as the delivery trajectory corresponding to the target historical order. Figure 4 As shown.

[0090] Figure 4 This is a schematic diagram of the delivery trajectory corresponding to a target historical order provided in this specification.

[0091] For example, the service platform identifies a target historical order that matches the AOI (Area of ​​Interest) of cell H, and determines, for example... Figure 4 The delivery trajectory shown is the path taken by the delivery capacity executing this target historical order. It can be seen that the delivery trajectory starts outside of Community H, passes the entrance of Community H, turns towards Building 1 within Community H, and then passes the exit of Community H to return to the outside of Community H. This delivery trajectory can be used as the delivery trajectory for this target historical order.

[0092] In other words, in this specification, the service platform does not focus on the entire delivery trajectory of a target historical order, but only on the delivery trajectory composed of trajectory points located near or inside the AOI, and then uses this part of the trajectory to determine the intersection with the AOI.

[0093] It should be noted that in practical applications, the trajectory points in the delivery tracks of the target historical order collected by the service platform may deviate from the actual delivery tracks of the target historical order. This could lead to inaccurate intersection points between the subsequently determined delivery tracks of the target historical order and the boundary of the AOI to be labeled. Figure 5As shown.

[0094] Figure 5 This is a schematic diagram of a noise point in a delivery trajectory provided in this specification.

[0095] When the following occurs Figure 5 When the trajectory point deviates significantly from the actual delivery trajectory of the target historical order, the intersection point determined by the service platform may not be the entrance or exit of the AOI to be labeled, which may ultimately lead to inaccurate determination of the entrance or exit of the AOI to be labeled.

[0096] To prevent the impact of the above situations, in this specification, the service platform needs to remove noise points from the delivery trajectory corresponding to the target historical order. Specifically, for each trajectory point in the delivery trajectory corresponding to the target historical order, if the distance between the trajectory point and its adjacent trajectory points is not less than a set distance, then the trajectory point is determined to be a noise point and removed from the delivery trajectory corresponding to the target historical order.

[0097] For example, such as Figure 5 The delivery route determined by the service platform contains a point that deviates significantly from the actual delivery route; this point is clearly a noise point. If the service platform sets the distance to 50m, and the distance between this point and its two adjacent points is no less than 50m, the service platform can determine this point as a noise point and remove it from the delivery route.

[0098] In addition, the service platform can also identify each trajectory point in the delivery trajectory corresponding to the target historical order as a noise point and remove it if the delivery speed of the delivery capacity for that historical order at that trajectory point is not less than the set speed.

[0099] Of course, the service platform can also use both of the above methods to remove noise points from the delivery trajectory corresponding to the target historical order. For example, if the service platform determines that there is a trajectory point in the delivery trajectory corresponding to the target order whose distance from all adjacent trajectory points is not less than a set distance, and the delivery speed of the delivery capacity for the target historical order at that trajectory point is not less than a set speed, then that trajectory point is determined to be a noise point and removed.

[0100] S104: Based on the delivery trajectory corresponding to the target historical order, determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, and use it as the intersection point corresponding to the target historical order.

[0101] Once the service platform determines the delivery trajectory corresponding to the target historical order, it can determine the intersection point between the delivery trajectory and the boundary of the AOI to be labeled, which will be used as the intersection point corresponding to the target historical order.

[0102] Since there may be situations where the delivery trajectory corresponding to the target historical order intersects the boundary of the AOI to be labeled, but the delivery trajectory does not enter the interior of the AOI to be labeled, the service platform needs to determine the intersection point where the delivery trajectory corresponding to the target historical order crosses the boundary of the AOI to be labeled and intersects with the boundary, and use this intersection point as the intersection point corresponding to the target historical order.

[0103] Specifically, the service platform can determine the intersection point between the delivery trajectory corresponding to the target's historical order and the boundary of the AOI to be labeled on a preset electronic map, and use this intersection point as the identification point. In this specification, the boundary of the AOI to be labeled refers to the boundary of the AOI to be labeled on the preset electronic map, such as... Figure 4 As shown. Correspondingly, when marking the entrances and exits of the AOI to be marked, it can also refer to marking the entrances and exits of the AOI to be marked on the electronic map.

[0104] Then, the service platform can further determine the trajectory points in the delivery trajectory that are adjacent to the intersection point to be identified and located outside the boundary of the AOI to be labeled, as the first trajectory points, and determine the trajectory points in the delivery trajectory corresponding to the target historical order that are adjacent to the intersection point to be identified and located inside the boundary of the AOI to be labeled, as the second trajectory points.

[0105] If the service platform determines that, among the trajectory points included in the delivery trajectory, there are no fewer than a first set number of continuous trajectory points adjacent to the first trajectory point outside the boundary of the AOI to be labeled, and no fewer than a second set number of continuous trajectory points adjacent to the second trajectory point inside the boundary of the AOI to be labeled, then the intersection point to be identified can be taken as the intersection point corresponding to the target historical order.

[0106] For example, such as Figure 4 The intersection of the delivery trajectory shown with the boundary of Community H on the electronic map forms a triangle. It can be seen that the trajectory point adjacent to this intersection point and located outside the boundary of Community H is the first trajectory point, and the trajectory point adjacent to this intersection point and located inside the boundary of Community H is the second trajectory point. If the service platform sets the first preset quantity to 1 and the second preset quantity to 2, it can be seen that there are at least one consecutive trajectory point adjacent to the first trajectory point outside the boundary of Community H, and at least two consecutive trajectory points adjacent to the second trajectory point inside the boundary of Community H. Therefore, this intersection point can be used as... Figure 4 The intersection of the target historical orders corresponding to the delivery trajectory shown.

[0107] It should be noted that the first and second preset quantities mentioned above can be set according to actual needs, and this specification does not limit the specific values ​​used for the first and second preset quantities. It is worth mentioning that the larger the values ​​of the first and second preset quantities, the more accurate the determined intersection point will be. Therefore, to ensure that the determined intersection point is more reasonable, the specific values ​​of the first and second preset quantities can be set to be larger.

[0108] S105: Based on the intersection points corresponding to the at least one target historical order, determine the entrance and exit of the AOI to be labeled and label it.

[0109] After the service platform determines the intersection point corresponding to at least one target historical order that matches the AOI to be labeled, it can determine the entrance and exit of the AOI to be labeled based on the intersection points corresponding to at least one target historical order and then label it.

[0110] Specifically, for each target historical order, if the intersection point corresponding to the target historical order meets the preset conditions, the service platform can use the intersection point corresponding to the target historical order as a candidate annotation point, and then determine the entrance and exit of the AOI to be annotated based on each candidate annotation point and annotate it.

[0111] Specifically, for each intersection point corresponding to a target historical order, the service platform can determine the line connecting the intersection point to the adjacent trajectory point in the delivery trajectory corresponding to that historical order. If the angle between this line and the perpendicular line on the boundary of the AOI to be labeled, where the intersection point is located, is determined to be no greater than a set angle, the intersection point is determined as a candidate labeling point that meets preset conditions, such as... Figure 6 As shown.

[0112] Figure 6 This is a schematic diagram of the intersection of a delivery trajectory and the boundary of an AOI to be labeled, as provided in this specification.

[0113] For example, such as Figure 6 As shown, when the service platform collects a delivery trajectory consisting of trajectory points A, B, C, D, and E, the intersection of this delivery trajectory with the boundary of cell H is intersection point C. After determining the lines connecting the adjacent trajectory points to intersection point C, it can be seen that the angle between the perpendicular line of the boundary where intersection point C is located (i.e., the upper boundary of AOI) and this connecting line is 40 degrees. If trajectory point C is missing due to positioning issues, and the service platform only collects the delivery trajectory consisting of trajectory points A, B, D, and E, the intersection of this delivery trajectory with the boundary of cell H is intersection point B. The lines connecting the adjacent trajectory points to intersection point B can be determined, and it can be seen that the angle between the perpendicular line of the boundary where intersection point B is located (i.e., the upper boundary of AOI) and this connecting line is 65 degrees.

[0114] If trajectory points B and C are missing due to positioning issues when the service platform collects delivery trajectories, then the determined delivery trajectory is the one formed by connecting trajectory points A, D, and E. The intersection of this delivery trajectory with the boundary of community H is intersection point A. The lines connecting the trajectory points adjacent to intersection point A to intersection point A can be determined, and it can be seen that the angle between the perpendicular line of the boundary where intersection point A is located (i.e., the upper boundary of AOI) and this connecting line is 80 degrees.

[0115] Based on this, it can be seen that intersection C is likely the location where the delivery personnel enter the H community. As for intersections A and B, due to missing trajectory points when the service platform collected delivery trajectories, these two intersections are unlikely to be entrances or exits of the H community. Therefore, the service platform sets the angle to 60 degrees, so that intersection C meets the preset conditions, while intersections A or B do not.

[0116] As can be seen from the examples above, the smaller the angle, the more likely the intersection is to be the location where the delivery capacity enters the AOI to be labeled during the delivery process. This means that the intersection is more likely to be the entrance or exit of the AOI to be labeled. Therefore, this preset condition can better filter the intersections that may be the entrance or exit of the AOI to be labeled.

[0117] The service platform can also identify each intersection point corresponding to the target historical order as a candidate annotation point that meets the preset conditions if it is determined that the distance between the intersection point and the adjacent trajectory points in the delivery trajectory corresponding to the target historical order does not exceed the set distance.

[0118] The service platform can also determine each intersection point corresponding to the target historical order as a candidate annotation point that meets preset conditions, based on the direction of travel of the delivery trajectory corresponding to the target historical order. If the intersection point is the first intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be annotated, or if the intersection point is the last intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be annotated, the intersection point can be determined as a candidate annotation point that meets preset conditions.

[0119] In other words, under normal circumstances, when delivery capacity enters the AOI to deliver the goods to the user and exits the AOI, the resulting delivery trajectory should intersect the boundary of the AOI at two points. Therefore, from the perspective of the delivery trajectory, the intersection point that meets the preset conditions should be either the first intersection point or the last intersection point between the delivery trajectory and the AOI.

[0120] As can be seen, the above are three preset conditions set by the service platform. In practical applications, the service platform can select the required preset conditions according to actual needs, and then filter the determined intersection points through the selected preset conditions to determine the candidate annotation points.

[0121] After identifying the candidate annotation points, the service platform can determine and annotate the entrances and exits of the AOI to be annotated from these candidate points. Specifically, the service platform can input each candidate annotation point into a preset screening model to determine the probability density distribution function representing the probability density of each candidate annotation point, and then identify each peak from the probability density distribution function. For each peak, if the peak value is determined to be not less than a set threshold, the candidate annotation point corresponding to that peak is used as the entrance / exit of the AOI to be annotated. The set threshold mentioned here can be determined by the service platform according to actual needs. The algorithm used by this screening model can be a clustering algorithm such as kernel density estimation, and is not specifically limited here.

[0122] like Figure 7 As shown.

[0123] Figure 7 This is a schematic diagram of a probability density distribution function provided in this specification.

[0124] For example, the candidate annotation points for cell H identified by the service platform are as follows: Figure 7 As shown on the left, most candidate markers are located at the upper and right boundaries of cell H, with a few candidate markers at the lower boundary. Therefore, the probability density distribution function plotted for cell H in the above example would be approximately: Figure 7 The distribution function on the right side of the middle.

[0125] As can be seen, the distribution function has three peaks. The first two peaks correspond to the dense clusters of candidate markers at the upper and right boundaries, while the last peak corresponds to two scattered candidate markers at the lower boundary. Since these scattered candidate markers are likely not entrances / exits of cell H, or not regular entrances / exits of cell H, the service platform can filter them out based on the distribution function. The service platform determines that the peak values ​​of the first two peaks are greater than a set threshold, while the peak value of the last peak is less than a set threshold. Therefore, based on the distribution function, the entrances / exits of cell H can be identified as the candidate markers corresponding to the first two peaks.

[0126] During the aforementioned process, the service platform identifies candidate annotation points that can serve as the entry and exit points of the AOI to be annotated. These candidate annotation points can be directly used as the entry and exit points of the AOI. It should be noted that if too few candidate annotation points are identified for the AOI within a set historical timeframe, the entry and exit points determined based on the probability density distribution function may be inaccurate due to insufficient sample size. Therefore, the service platform can determine the number of candidate annotation points for the AOI within a set historical timeframe. If this number is less than the set number, the entry and exit points of the AOI will not be annotated.

[0127] As can be seen from the above, the service platform can determine and mark the entrances and exits of the AOI to be marked based on several historical delivery trajectories that have passed through it and the intersection points of these trajectories with the boundary of the AOI. The service platform can identify potential entrances and exits of the AOI from these intersection points and further determine the actual entrances and exits using a preset filtering model. This allows for a relatively accurate determination of the AOI's entrances and exits. Therefore, this method can automatically determine the entrances and exits of the AOI to be marked using historical data, thereby improving delivery efficiency to some extent.

[0128] After the service platform identifies the entrances and exits of each AOI to be labeled, it can use these labeled entrances and exits to plan routes for delivery capacity to perform order delivery tasks. The specific process is as follows: Figure 8 As shown.

[0129] Figure 8 This document provides a flowchart illustrating a route planning method, which includes the following steps:

[0130] S801: Receive the user's target order.

[0131] S802: Based on the delivery address of the target order, determine the AOI to which the target order belongs, and use it as the target AOI.

[0132] In this specification, the service platform can receive a user's target order and determine the AOI (Area of ​​Interest) to which the target order belongs based on the delivery address of the target order. Here, the target order refers to the order placed by the user based on their actual needs. The AOI to which the target order belongs is the AOI of the delivery address of the target order.

[0133] S803: Based on the entrances and exits marked in the target AOI, plan the delivery route for the target order.

[0134] S804: Recommend the planned delivery route to the delivery capacity that will execute the target order.

[0135] If the service platform has already marked the entrance and exit of the target AOI, it can plan the delivery route for the target order based on the marked entrance and exit of the target AOI, and recommend the planned delivery route to the delivery capacity that will execute the target order.

[0136] Since a target AOI often has multiple entry / exit points, the service platform can select at least one entry / exit point as the target entry / exit point from these points based on the historical orders associated with that AOI. These historical orders refer to those with delivery addresses belonging to that AOI. For these historical orders, the service platform can obtain the routes taken by the delivery personnel executing these orders. Based on these routes, it can further determine which entry / exits are frequently used by the delivery personnel and select them as target entry / exits. The service platform can then plan a delivery route through the target entry / exit point and recommend this route to the delivery personnel executing the target orders. This allows the delivery personnel to deliver the goods corresponding to the target orders to the users more efficiently.

[0137] Of course, the service platform can select target entrances / exits in various ways. Besides the methods mentioned above, it can also select them based on the status information of each entrance / exit corresponding to the target AOI. In practical applications, each entrance / exit of an AOI is not always open; some may be temporarily closed due to special circumstances. Therefore, the status information of each entrance / exit corresponding to the target AOI can be used to characterize whether the entrance / exit is open. Based on this, the service platform can select the open entrances / exits as target entrances / exits based on the obtained status information. There are several ways to obtain the status information of entrances / exits; for example, it can be through manual information reporting or by using historical orders to determine the status information. Other methods for selecting target entrances / exits will not be listed here.

[0138] The above describes one or more embodiments of the methods for entrance / exit marking and route planning provided in this specification. Based on the same concept, this specification also provides corresponding devices for entrance / exit marking and route planning, such as... Figure 9 , 10 As shown.

[0139] Figure 9 This specification provides a schematic diagram of an entrance / exit labeling device, which specifically includes:

[0140] The first determining module 901 is configured to determine each region of interest (AOI) to be labeled.

[0141] The acquisition module 902 is configured to acquire at least one target historical order that matches each AOI to be labeled.

[0142] The second determining module 903 is configured to determine, for each target historical order, the delivery trajectory traversed by the delivery capacity executing the target historical order during the execution of the target historical order, and use it as the delivery trajectory corresponding to the target historical order.

[0143] The third determining module 904 is configured to determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, based on the delivery trajectory corresponding to the target historical order, and use it as the intersection point corresponding to the target historical order.

[0144] The annotation module 905 is configured to determine the entrance and exit of the AOI to be annotated based on the intersection points corresponding to the at least one target historical order and to annotate them.

[0145] Optionally, the acquisition module 902 is configured to determine the delivery location of the corresponding delivery for each historical order; determine the AOI to which the delivery location falls through a preset AOI search tree; and use the historical order as a target historical order that matches the AOI to which the delivery location falls.

[0146] Optionally, the third determining module 904 is configured to determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled on a preset electronic map, as the intersection point to be identified; determine, in the delivery trajectory corresponding to the target historical order, a trajectory point adjacent to the intersection point to be identified and located outside the boundary of the AOI to be labeled, as the first trajectory point; and determine, in the delivery trajectory corresponding to the target historical order, a trajectory point adjacent to the intersection point to be identified and located inside the boundary of the AOI to be labeled, as the second trajectory point; and if, among the trajectory points included in the delivery trajectory corresponding to the target historical order, it is determined that there are at least a first set number of consecutive trajectory points adjacent to the first trajectory point outside the boundary of the AOI to be labeled, and at least a second set number of consecutive trajectory points adjacent to the second trajectory point inside the boundary of the AOI to be labeled, then the intersection point to be identified is taken as the intersection point corresponding to the target historical order.

[0147] Optionally, the annotation module 905 is configured to, for each target historical order, if it is determined that the intersection point corresponding to the target historical order meets the preset conditions, take the intersection point corresponding to the target historical order as a candidate annotation point; and determine the entrance and exit of the AOI to be annotated and annotate it based on the candidate annotation point.

[0148] Optionally, the annotation module 905 is configured to, for each intersection point corresponding to the target historical order, determine the trajectory points adjacent to the intersection point in the delivery trajectory corresponding to the target historical order, and determine the line connecting the trajectory points adjacent to the intersection point and the intersection point; if it is determined that the angle between the line connecting the intersection point and the perpendicular line on the boundary of the AOI to be annotated where the intersection point is located is not greater than a set angle, the intersection point is determined to be a candidate annotation point that meets the preset conditions.

[0149] Optionally, the annotation module 905 is configured to, for each intersection point corresponding to the target historical order, if it is determined that the distance between the intersection point and the adjacent trajectory point in the delivery trajectory corresponding to the target historical order does not exceed a set distance, determine the intersection point as a candidate annotation point that meets the preset conditions.

[0150] Optionally, the annotation module 905 is configured to input each candidate annotation point into a preset screening model, determine a probability density distribution function to characterize the probability density of each candidate annotation point; determine each peak from the probability density distribution function; and for each peak, if it is determined that the peak value of the peak is not less than a set threshold, annotate the candidate annotation point corresponding to the peak as the entrance / exit of the AOI to be annotated.

[0151] Optionally, the second determining module 903 is configured to remove each trajectory point from the delivery trajectory corresponding to the target historical order if the distance between the trajectory point and its adjacent trajectory points is not less than a set distance.

[0152] Optionally, the second determining module 903 is configured to, for each trajectory point in the delivery trajectory corresponding to the target historical order, if the delivery speed of the delivery capacity executing the target historical order at that trajectory point is not less than a set speed, then determine that the trajectory point as a noise point and remove the trajectory point.

[0153] As can be seen from the above device, since it can determine and mark the entrance and exit of the AOI to be marked based on several historical delivery trajectories that have passed through it and the intersection points of these delivery trajectories with the boundary of the AOI, this device can automatically determine the entrance and exit of the AOI to be marked using historical data, thereby improving delivery efficiency to a certain extent.

[0154] Figure 10 A schematic diagram of a route planning device provided in this specification specifically includes:

[0155] The receiving module 1001 is configured to receive the user's target order;

[0156] The determination module 1002 is configured to determine the AOI to which the target order belongs based on the delivery address of the target order, and use it as the target AOI;

[0157] The planning module 1003 is configured to plan the delivery route of the target order based on the entrances and exits marked in the target AOI, wherein the entrances and exits of the target AOI are marked using the aforementioned entrance and exit marking method.

[0158] The recommendation module 1004 is configured to recommend planned delivery routes to delivery capacity that executes the target order.

[0159] Optionally, the planning module 1003 is configured to select a target entrance / exit from the entrances / exits marked in the target AOI based on the historical orders corresponding to the target AOI; and plan a delivery route through the target entrance / exit based on the target entrance / exit.

[0160] As can be seen from the above device, after receiving a user's target order, the service platform can recommend a delivery route to the delivery capacity that is executing the target order based on the entrance and exit of the target AOI to which the target order belongs. This will greatly facilitate the delivery capacity to execute the delivery task of the target order and effectively improve the order execution efficiency of the delivery capacity.

[0161] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The provided method for entrance / exit labeling or the above Figure 8 The provided route planning method.

[0162] This instruction manual also provides Figure 11 The diagram shows a schematic structural representation of the electronic device. Figure 11 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The method for marking entrances and exits, or the method described above. Figure 8 The method for route planning described above. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0163] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0164] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0165] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0166] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0167] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0168] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0169] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0170] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0171] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0172] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0173] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0174] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0175] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0176] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0177] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0178] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for marking entrances and exits, characterized in that, include: Identify the regions of interest (AOIs) to be labeled; For each AOI to be labeled, obtain at least one target historical order that matches that AOI; For each target historical order, determine the delivery trajectory traversed by the delivery capacity executing the target historical order during its execution. Extract the portion of the delivery trajectory from the entry to the AOI to the exit of the AOI as the delivery trajectory corresponding to the target historical order. Based on the delivery trajectory corresponding to the target historical order, determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, and use this intersection point as the intersection point corresponding to the target historical order. Based on the intersection point corresponding to the at least one target historical order, determine the line connecting the intersection point to the adjacent trajectory point in the delivery trajectory corresponding to the target historical order. If the angle between the connecting line and the perpendicular line on the boundary of the AOI to be labeled located at the intersection point is not greater than a set angle, the intersection point is determined as a candidate labeling point that meets the preset conditions; or, for the intersection point corresponding to the target historical order, if the distance between the intersection point and the adjacent trajectory point in the delivery trajectory corresponding to the target historical order does not exceed a set distance, the intersection point is determined as a candidate labeling point that meets the preset conditions. Each candidate annotation point is input into a preset screening model to determine the probability density distribution function used to characterize the probability density of each candidate annotation point. Each peak is determined from the probability density distribution function. If the peak value of the peak is not less than a set threshold, the candidate annotation point corresponding to the peak is used as the entrance and exit of the AOI to be annotated and annotated.

2. The method as described in claim 1, characterized in that, For each AOI to be labeled, obtaining at least one target historical order that matches that AOI includes: For each historical order, determine the delivery location of the corresponding shipment; The AOI into which the delivery location falls is determined by using a preset AOI search tree; This historical order is used as the target historical order that matches the AOI to which the delivery location falls.

3. The method as described in claim 1, characterized in that, The step of determining the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, based on the delivery trajectory corresponding to the target historical order, includes: The intersection point between the delivery trajectory corresponding to the target's historical order and the boundary of the AOI to be labeled on the preset electronic map is determined as the intersection point to be identified. In the delivery trajectory corresponding to the target historical order, determine the trajectory point that is adjacent to the intersection point to be identified and located outside the boundary of the AOI to be labeled, as the first trajectory point; and determine the trajectory point that is adjacent to the intersection point to be identified and located inside the boundary of the AOI to be labeled, as the second trajectory point. If, among the trajectory points included in the delivery trajectory corresponding to the target historical order, it is determined that there are no less than a first set number of continuous trajectory points adjacent to the first trajectory point outside the boundary of the AOI to be labeled, and no less than a second set number of continuous trajectory points adjacent to the second trajectory point inside the boundary of the AOI to be labeled, the intersection point to be identified is taken as the intersection point corresponding to the target historical order.

4. The method of claim 1, further comprising: For each trajectory point in the delivery trajectory corresponding to the target historical order, if the distance between the trajectory point and its adjacent trajectory points is not less than a set distance, the trajectory point is removed from the delivery trajectory corresponding to the target historical order.

5. The method of claim 1, further comprising: For each trajectory point in the delivery trajectory corresponding to the target historical order, if the delivery speed of the delivery capacity for the target historical order at that trajectory point is not less than the set speed, then that trajectory point is removed from the delivery trajectory corresponding to the target historical order.

6. A route planning method, characterized in that, include: Receive the user's target order; Based on the delivery address of the target order, determine the AOI to which the target order belongs, and designate it as the target AOI; Based on the entrances and exits marked in the target AOI, the delivery route of the target order is planned, wherein the entrances and exits of the target AOI are marked by any one of the methods in claims 1 to 5 above; The planned delivery routes are recommended to the delivery capacity that will fulfill the target order.

7. The route planning method as described in claim 6, characterized in that, The step of planning the delivery route for the target order based on the entrances and exits marked in the target AOI includes: Based on the historical orders corresponding to the target AOI, select the target entrance / exit from each entrance / exit marked in the target AOI; Based on the target entrance / exit, a delivery route is planned that passes through the target entrance / exit.

8. A device for marking entrances and exits, characterized in that, include: The first determination module is configured to determine each region of interest (AOI) to be labeled. The acquisition module is configured to acquire at least one target historical order that matches each AOI to be labeled. The second determining module is configured to determine, for each target historical order, the delivery trajectory traversed by the delivery capacity executing the target historical order during the execution of the target historical order, and extract the part of the delivery trajectory from the delivery capacity from entering the AOI to leaving the AOI to be labeled as the delivery trajectory corresponding to the target historical order. The third determining module is configured to determine the intersection point between the delivery trajectory corresponding to the target historical order and the boundary of the AOI to be labeled, based on the delivery trajectory corresponding to the target historical order, and use it as the intersection point corresponding to the target historical order; The annotation module is configured to determine, based on the intersection point corresponding to the at least one target historical order, the line connecting the trajectory point adjacent to the intersection point in the delivery trajectory corresponding to the target historical order and the intersection point; if the angle between the line connecting the intersection point and the perpendicular line on the boundary of the AOI to be annotated located at the intersection point is not greater than a set angle, the intersection point is determined to be a candidate annotation point that meets preset conditions; or, for the intersection point corresponding to the target historical order, if the distance between the intersection point and the adjacent trajectory point in the delivery trajectory corresponding to the target historical order is not greater than a set distance, the intersection point is determined to be a candidate annotation point that meets preset conditions. Each candidate annotation point is input into a preset screening model to determine the probability density distribution function used to characterize the probability density of each candidate annotation point. Each peak is determined from the probability density distribution function. If the peak value of the peak is not less than a set threshold, the candidate annotation point corresponding to the peak is used as the entrance and exit of the AOI to be annotated and annotated.

9. A route planning device, characterized in that, include: A receiving module configured to receive user target orders; The determination module is configured to determine the AOI to which the target order belongs based on the delivery address of the target order, and use it as the target AOI; A planning module is configured to plan the delivery route of the target order based on the entrances and exits marked in the target AOI, wherein the entrances and exits of the target AOI are marked by any one of the methods of claims 1 to 5 above; The recommendation module is configured to recommend planned delivery routes to delivery capacity that will execute the target order.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 5 or 6 to 7.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 5 or 6 to 7.

Images