A method and system for delineating the outline of an area of ​​interest

Abstract

An embodiment of the present specification provides a method and system for depicting the outline of an area of ​​interest, the method comprising: selecting multiple pick-up points related to the area of ​​interest; obtaining at least two historical orders at each pick-up point, and obtaining the pick-up trajectory of the driver in each of the historical orders; based on the pick-up trajectory of the driver in the two or more historical orders at the same pick-up point, obtaining overlapping sub-trajectories in the two or more pick-up trajectories; and depicting the outline of the area of ​​interest based on the overlapping sub-trajectories of the multiple pick-up points.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of computer technology, and more particularly, to a method and system for depicting the outline of a region of interest. Background Art

[0002] The area of ​​interest, or AOI (Area of ​​Interest), refers to a regional geographic entity in the map data, such as the Capital Space, the Summer Palace, Peking University, etc. The area of ​​interest is a planar area, and the outline of the area of ​​interest is the boundary outline of the planar area. At present, the determination of the outline of the area of ​​interest on the map is mainly based on the drawing of manually collected data, which makes the outline of the area of ​​interest low in accuracy. Due to the low accuracy of the outline of the area of ​​interest, when the boarding point is recommended on the taxi software, the recommended boarding point may be far away from the passenger or driver, which will affect the passenger's riding experience or increase the driver's detour cost. Therefore, how to improve the accuracy of the outline of the area of ​​interest is a problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0003] One of the embodiments of the present specification provides a method for depicting the outline of an area of ​​interest, the method comprising: selecting multiple pick-up points related to the area of ​​interest; obtaining at least two historical orders at each pick-up point, and obtaining the pick-up trajectories of the drivers in each of the historical orders; based on the pick-up trajectories of the drivers in the two or more historical orders at the same pick-up point, obtaining overlapping sub-trajectories in the two or more pick-up trajectories; and depicting the outline of the area of ​​interest based on the overlapping sub-trajectories of the multiple pick-up points.

[0004] One of the illustrative embodiments provides a system for delineating the outline of an area of ​​interest, the system comprising: a point selection module for selecting multiple boarding points related to the area of ​​interest; an order acquisition module for acquiring at least two historical orders at each boarding point, and obtaining the pick-up trajectory of the driver in each of the historical orders; a trajectory acquisition module for obtaining overlapping sub-trajectories in more than two pick-up trajectories based on the pick-up trajectories of the driver in the more than two historical orders at the same boarding point; and a contour drawing module for delineating the outline of the area of ​​interest based on the overlapping sub-trajectories of the multiple boarding points.

[0005] One of the illustrative embodiments provides a device for delineating the outline of an area of ​​interest, the device comprising a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device causes the device to implement operations corresponding to the method described in any of the above technical solutions.

[0006] Another embodiment of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When the computer reads the computer-executable instructions in the storage medium, the computer executes the method described in any of the above technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] One or more embodiments of the present specification will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1 is an exemplary flow chart of a method for depicting a region of interest according to some embodiments of the present specification;

[0009] Figure 2 A module diagram of a system for depicting a region of interest according to some embodiments of the present specification;

[0010] Figure 3 The figure is a schematic diagram of the outline of the region of interest drawn according to some embodiments of the present description. DETAILED DESCRIPTION

[0011] In order to more clearly illustrate the technical solutions of one or more embodiments of the specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the specification. For ordinary technicians in this field, one or more embodiments of the specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0012] It should be understood that the "system", "system", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0013] As shown in one or more embodiments and claims of this specification, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not specifically refer to the singular, but may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0014] In one or more embodiments of the specification, a flow chart is used to illustrate the operations performed by the system according to one or more embodiments of the specification. It should be understood that the previous or subsequent operations are not necessarily performed precisely in order. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] The embodiments of the present application relate to a method and system for depicting the outline of an area of ​​interest. The method selects multiple boarding points related to the area of ​​interest, and then obtains overlapping sub-trajectories of the pick-up trajectories of more than two drivers from the historical orders at each boarding point, and then uses these overlapping sub-trajectories to describe the outline of the area of ​​interest. In the method of the present application, the overlapping sub-trajectories used to depict the outline of the area of ​​interest are the result of superimposing the real driving trajectories of at least two drivers, which basically eliminates the problem of inaccurate trajectories caused by signal reasons. The authenticity of the overlapping sub-trajectories is high, so that the accuracy of the outline of the depicted area of ​​interest is high. One or more embodiments of the present specification can be applied to the outline of any area of ​​interest with historical order data for its related boarding points, and the outline can be used in navigation software, taxi software and other software, which is conducive to improving the accuracy of functions such as navigation, location recommendation, and distance calculation in such software.

[0016] Figure 1 The present invention is an exemplary flow chart of a method for drawing the outline of an area of ​​interest according to some embodiments of the present specification. Specifically, the method for drawing the outline of an area of ​​interest can be executed by a processing device. For example, the method for drawing the outline of an area of ​​interest can be stored in a storage device (such as a storage device or a memory of a terminal for drawing the outline of an area of ​​interest) in the form of a program or an instruction. When a system for drawing the outline of an area of ​​interest (such as a processing device) executes the program or the instruction, the method for drawing the outline of an area of ​​interest can be implemented. Figure 1 As shown, the method of outlining the region of interest may include:

[0017] Step 110 , selecting a plurality of boarding points related to the area of ​​interest. Specifically, step 110 may be performed by the point selection module 210 .

[0018] In step 110, in addition, the number of boarding points selected by the point selection module 210 can be 5, 10 or 18, etc. Generally, the more boarding points selected by the point selection module 210, the more conducive to improving the accuracy of the delineation of the area of ​​interest. In addition, when the point selection module 210 selects the boarding points, the boarding points with more historical orders can be selected, which is also conducive to improving the accuracy of the delineation of the area of ​​interest.

[0019] In some embodiments, the boarding point associated with the area of ​​interest includes a boarding point whose distance from the area of ​​interest is within a preset distance range, and / or a boarding point whose name matches the name of the area of ​​interest. Those skilled in the art can set the preset distance range according to actual needs, for example, it can be set to 0-30m, 0-50m, etc. If the preset distance range is set to 0-50m, when the distance between the boarding point and the area of ​​interest is within the range of 0-50m, for example, when the distance between the boarding point and the area of ​​interest is 20m, 35m or 45m, etc., the boarding point is considered to be a boarding point associated with the area of ​​interest. The matching of the boarding point with the name of the area of ​​interest can be understood as the name of the boarding point being identical or partially identical to the name of the area of ​​interest in terms of text. For example, when the area of ​​interest is Peking University, if the name of the boarding point is Peking University West Gate, then it can be considered that the name of the boarding point matches the name of the area of ​​interest.

[0020] Step 120 , obtaining at least two historical orders at each pick-up point, and obtaining the driver's pick-up track in each historical order. Specifically, step 120 is performed by the order acquisition module 220 .

[0021] In step 120, the driver's pick-up trajectory is the driving trajectory information of the driver's pick-up. During the pick-up process, the driver may drive along the outline of the area of ​​interest, so the driving trajectory information can provide a reference for delineating the outline of the area of ​​interest. In this embodiment, the order acquisition module 220 can obtain any number of historical orders of more than two, for example, 50, 80, 200, etc. In general, the more historical orders the order acquisition module 220 obtains, the more conducive it is to improving the accuracy of the outline delineation.

[0022] In some embodiments, since the driver may be far away from the pick-up point when receiving the order, there may be a long driving trajectory in the pick-up trajectory that is unrelated to the contour of the area of ​​interest, so it is necessary to truncate or extract the driver's pick-up trajectory. In some embodiments, the driver's pick-up trajectory includes: a driving trajectory within a preset time range before the driver picks up the passenger and after the driver picks up the passenger, or a driving trajectory within a preset length range before the driver picks up the passenger and after the driver picks up the passenger. Those skilled in the art can set the preset time range and preset length range according to specific needs, for example, it can be 3s before the driver picks up the passenger and 3s after the driver picks up the passenger. In addition, the preset time range before and after the driver picks up the passenger can be different, for example, it can be 4s before the driver picks up the passenger and 5s after the driver picks up the passenger. For another example, it can be 2km before the driver picks up the passenger and 2km after the driver picks up the passenger. In addition, the preset length range before and after the driver picks up the passenger can be different, or the driver picks up the passenger before the 1.5km, and the driver picks up the passenger after the 2.5km.

[0023] In some embodiments, step 120 also includes: after obtaining at least two historical orders at each boarding point and obtaining the pick-up track of the driver in each historical order, the historical orders whose pick-up track does not meet the second preset condition are excluded. Since the driver may have inaccurate positioning or missing positioning signals, the driver's pick-up track in the historical order may be inaccurate and cannot truly reflect the outline of the area of ​​interest. Therefore, after the order acquisition module 220 obtains the pick-up track of the driver in each historical order, these inaccurate pick-up tracks are excluded to ensure the accuracy of the outline of the area of ​​interest obtained in the end. Specifically, the order acquisition module 220 can use the second preset condition to determine whether the driver's pick-up track in the historical order is accurate.

[0024] In some embodiments, the second preset condition includes: there are no jumping trajectory points. The driver's pick-up trajectory is composed of multiple trajectory points, and these trajectory points are connected in sequence to form a trajectory. Therefore, when the driver's end has inaccurate positioning or missing positioning signals, the positions of one or more trajectory points may deviate from the entire pick-up trajectory. At this time, it can be considered that the entire pick-up trajectory is inaccurate, and the order acquisition module 220 can exclude the historical orders corresponding to the pick-up trajectory. In some alternative embodiments, the second preset condition may also include: the pick-up trajectory is not interrupted. The pick-up trajectory should be continuous. When the pick-up trajectory is interrupted, it may be caused by the long-term absence of the positioning signal on the driver's end. At this time, it can be judged that the accuracy of the entire pick-up trajectory is low, and the order acquisition module 220 can exclude the historical orders corresponding to the pick-up trajectory.

[0025] Step 130 , based on the pick-up trajectories of the driver in two or more historical orders at the same pick-up point, obtain overlapping sub-trajectories in the two or more pick-up trajectories. Specifically, step 130 is performed by the trajectory acquisition module 230 .

[0026] In this embodiment, the method for the trajectory acquisition module 230 to obtain overlapping sub-trajectories in more than two pick-up trajectories can be to obtain them through a model obtained by machine learning, or to obtain them by directly deduplicating and merging multiple trajectory points of the pick-up trajectories of more than two drivers.

[0027] In some embodiments, when the model obtained by machine learning is used to obtain overlapping sub-trajectories, based on the pick-up trajectories of the drivers in more than two historical orders of the same boarding point, the overlapping sub-trajectories in the pick-up trajectories are obtained, including: splitting the pick-up trajectory of the driver in each historical order into multiple sub-trajectories according to the first preset length to obtain a trajectory set for each historical order; obtaining an overlapping sub-trajectory recognition model; inputting the trajectory set of each historical order into the overlapping sub-trajectory recognition model, and identifying the overlapping overlapping sub-trajectories in the trajectory set by the overlapping sub-trajectory recognition model. It can be understood that those skilled in the art can set the first preset length according to the actual situation, and the present application does not further limit this. For example, the first preset length can be further determined according to the length of the pick-up trajectory selected in each historical order. When the length of the pick-up trajectory selected in each historical order is longer, the first preset length can be set to be longer; for another example, the first preset length can be further determined according to the number or density of the boarding points selected in step 110. When the selected boarding points are more or more dense, the first preset length can be set to be shorter. In addition, the overlapping sub-trajectory recognition model will be further described below.

[0028] In some embodiments, the overlapping sub-trajectory recognition model is generated by training the initial model so that the overlapping sub-trajectory recognition model can accurately identify the overlapping sub-trajectories in the trajectory set of each historical order. Specifically, the training process includes: obtaining the known contour of the area of ​​interest; obtaining multiple historical orders at the boarding points related to the area of ​​interest, and taking the driver's pick-up trajectory in each historical order as a training sample; training the initial model based on the training samples and the known contours to obtain the overlapping sub-trajectory recognition model. It should be noted that the known contour of the area of ​​interest can be a contour obtained based on manual collection, or it can be a contour obtained by contouring using the method of the present application last time. During the training process, the pick-up trajectories of the drivers in multiple historical orders are used as training samples, and the driver's pick-up trajectory is compared with the known contour of the area of ​​interest, thereby completing the training of the initial model.

[0029] In some embodiments, the initial model is trained based on the training samples and the known contours to obtain the overlapping sub-trajectory recognition model, including: splitting the pick-up trajectory of each training sample into multiple sub-trajectories according to the second preset length to obtain a trajectory set of each training sample; using whether each sub-trajectory in the trajectory set of each training sample overlaps with the known contour as a label to classify each sub-trajectory, and optimizing and iterating the initial model according to each sub-trajectory and the corresponding label to obtain the overlapping sub-trajectory recognition model. In this embodiment, those skilled in the art can determine the second preset length according to the actual situation, and the present application does not further limit this. Specifically, the second preset length can be the same as the first preset length or different from the first preset length. As an example only, the second preset length can be further determined according to the length of the pick-up trajectory selected in each historical order. When the length of the pick-up trajectory selected in each historical order is longer, the second preset length can be set to be longer; in addition, the second preset length can also be further determined according to the number or density of the boarding points selected in step 110. When the selected boarding points are more or more dense, the second preset length can be set to be shorter. The sub-trajectories in the trajectory set of each training sample are used as features, and whether each sub-trajectory overlaps with a known contour is used as a label. The sub-trajectories that can overlap with the known contour are labeled "1", and the sub-trajectories that cannot overlap with the known contour are labeled "0", so as to classify each sub-trajectory in the trajectory set. The trajectory set is traversed multiple times using the training algorithm in the model, and each sub-trajectory in the trajectory set is classified multiple times. During the multiple traversal processes, the model can be iteratively optimized by gradient descent method, conjugate gradient method or Newton iteration method, so as to obtain an overlapping sub-trajectory recognition model that can accurately classify sub-trajectories.

[0030] In some embodiments, when multiple trajectory points of the pick-up trajectories of more than two drivers are deduplicated and merged to obtain overlapping sub-trajectories, the overlapping sub-trajectories in the pick-up trajectories of more than two drivers in more than two historical orders at the same boarding point are obtained, including: obtaining the overlapping trajectory points in the pick-up trajectories of the drivers in more than two historical orders; selecting multiple overlapping trajectory points that meet the first preset condition; connecting the selected multiple overlapping trajectory points to obtain overlapping sub-trajectories. The above-mentioned overlapping trajectory points can be understood as trajectory points with exactly the same coordinates on the pick-up trajectory. Those skilled in the art can set the first preset condition according to the actual situation, and the present application does not impose further restrictions on this. Since the actual driving trajectory of the driver's pick-up may be affected by the strength of the positioning signal, traffic conditions, and some sudden unexpected situations, the first preset condition is set to select accurate and representative trajectory points, so that the overlapping sub-trajectory obtained by connecting multiple overlapping trajectory points can reflect the outline of the actual area of ​​interest.

[0031] In some embodiments, the first preset condition includes: matching with the known contour of the area of ​​interest. That is, in the process of selecting the overlapping trajectory points, the known contour of the area of ​​interest is used as a reference to select the overlapping trajectory points that fall on the known contour of the area of ​​interest, so that the final overlapping sub-trajectory obtains multiple confirmations of the known contour and the actual driving paths of multiple drivers. In this embodiment, the overlapping trajectory points are obtained by the pick-up trajectories of drivers in more than two historical orders. The overlapping trajectory points may be the overlapping trajectory points of the pick-up trajectories of 2 drivers, or the overlapping trajectory points of the pick-up trajectories of 50 drivers. In some alternative embodiments, the first preset condition may also include: the number of pick-up trajectories for obtaining the overlapping trajectory points is greater than the first preset threshold. For example, the first preset threshold can be set to 50, that is, when the pick-up trajectories of more than 50 drivers overlap on the overlapping trajectory point, the overlapping trajectory point is selected. Of course, those skilled in the art can set the first preset threshold to other values ​​according to the number of historical orders, such as 20, 80, 100, etc.

[0032] Step 140 , based on the overlapping sub-trajectories of the multiple boarding points, draw the outline of the area of ​​interest. Specifically, step 140 is performed by the outline drawing module 240 .

[0033] In this embodiment, after the overlapping sub-trajectories of multiple boarding points are obtained, these overlapping sub-trajectories can actually reflect the outline of the area of ​​interest, so the overlapping sub-trajectories of multiple boarding points can actually serve as part of the outline of the area of ​​interest. In some embodiments, the overlapping sub-trajectories may include overlapping points and / or overlapping road sections. In step 140, the outline drawing module 240 may select overlapping points to draw the outline of the area of ​​interest, may select overlapping road sections to draw the outline of the area of ​​interest, or may select both overlapping points and overlapping road sections to draw the outline of the area of ​​interest. Those skilled in the art may make a selection based on the specific location distribution of the overlapping points and overlapping road sections.

[0034] In some embodiments, based on the overlapping sub-trajectories of multiple boarding points, the outline of the region of interest is drawn, including: selecting an overlapping sub-trajectory as a starting sub-trajectory; selecting the overlapping sub-trajectory closest to the starting sub-trajectory as a second sub-trajectory; selecting overlapping sub-trajectories in sequence, so that the overlapping sub-trajectory selected each time is the overlapping sub-trajectory with the shortest distance from the overlapping sub-trajectory selected last time; connecting all the selected overlapping sub-trajectories in sequence to form a closed-loop region, thereby obtaining the outline of the region of interest. The overlapping sub-trajectory used as the starting sub-trajectory can be selected arbitrarily, the second sub-trajectory can be selected from the overlapping sub-trajectory with the shortest distance from the starting sub-trajectory, and the overlapping sub-trajectory selected thereafter can be selected from the overlapping sub-trajectory with the shortest distance from the overlapping sub-trajectory selected last time, so that the distance between adjacent overlapping sub-trajectories can be guaranteed to be the shortest, and the outline drawing error caused by connecting adjacent overlapping sub-trajectories can be reduced. In addition, when the overlapping sub-trajectories are overlapping road sections, the method for the contour drawing module 240 to determine the distance between the two overlapping sub-trajectories may be: along one direction (e.g., clockwise or counterclockwise) of the contour of the region of interest, determine the distance between the end point of the preceding overlapping sub-trajectory and the starting point of the following overlapping sub-trajectory, and the two overlapping sub-trajectories do not overlap or intersect. The method for sequentially connecting all the overlapping sub-trajectories selected by the contour drawing module 240 may be along one direction (e.g., clockwise or counterclockwise) of the contour of the region of interest, connect the end point of the preceding overlapping sub-trajectory with the starting point of the following overlapping sub-trajectory. Figure 3 is a schematic diagram of the outline of the region of interest drawn according to some embodiments of the present description, such as Figure 3 As shown, it is only an example. The solid lines in the figure are selected overlapping sub-trajectories, and the dotted lines in the figure are line segments used to connect adjacent overlapping sub-trajectories. Among them, the starting sub-trajectory is n1, and the second sub-trajectory is n2. The starting sub-trajectory n1 and the second sub-trajectory n2 can be connected by the line segment m1. In this way, multiple overlapping sub-trajectories are sequentially connected by line segments, and finally the outline of the area of ​​interest is enclosed.

[0035] The process 100 of the method for delineating a region of interest of the present application may further include the steps of calculating the accuracy of the contour of the region of interest obtained in step 140; if the accuracy is greater than or equal to a second preset threshold, replacing the existing contour of the region of interest with the contour of the region of interest obtained in step 140; if the accuracy is lower than the second preset threshold, re-delineating the contour of the region of interest. The second preset threshold may be set to 95%, 98%, 99%, etc. The method for calculating the accuracy of the contour of the region of interest may be to use a machine learning model or to perform manual calculation.

[0036] Figure 2 FIG. 1 is a block diagram of a system for depicting an area of ​​interest according to some embodiments of the present specification. Figure 2As shown, the system for depicting an area of ​​interest includes a point selection module 210 , an order acquisition module 220 , a trajectory acquisition module 230 and a contour depiction module 240 .

[0037] The point selection module 210 can be used to select multiple pick-up points related to the area of ​​interest. The order acquisition module 220 can be used to obtain at least two historical orders at each pick-up point, and obtain the driver's pick-up trajectory in each historical order. The trajectory acquisition module 230 can be used to obtain overlapping sub-trajectories in more than two pick-up trajectories based on the driver's pick-up trajectory in more than two historical orders for the same pick-up point. In some embodiments, the trajectory acquisition module 230 can be used to obtain overlapping points or overlapping road sections. The outline drawing module 240 can be used to draw the outline of the area of ​​interest based on the overlapping sub-trajectories of multiple pick-up points.

[0038] In some embodiments, the trajectory acquisition module 230 is further used to: split the driver's pick-up trajectory in each historical order into multiple sub-trajectories according to a first preset length to obtain a trajectory set for each historical order; obtain an overlapping sub-trajectory recognition model; input the trajectory set of each historical order into the overlapping sub-trajectory recognition model, and identify the overlapping sub-trajectories in the trajectory set that overlap with each other through the overlapping sub-trajectory recognition model.

[0039] In some embodiments, the overlapping sub-trajectory recognition model is generated according to a training process, which includes: obtaining a known outline of an area of ​​interest; obtaining multiple historical orders at pick-up points related to the area of ​​interest, and using the driver's pick-up trajectory in each historical order as a training sample; and training an initial model based on the training samples and the known outline to obtain the overlapping sub-trajectory recognition model.

[0040] In some embodiments, an initial model is trained based on training samples and known contours to obtain a trained model, including: splitting the pick-up trajectory of each training sample into multiple sub-trajectories according to a second preset length to obtain a trajectory set for each training sample; using whether each sub-trajectory in the trajectory set of each training sample overlaps with the known contour as a label to classify each sub-trajectory, and optimizing and iterating the initial model according to each sub-trajectory and the corresponding label to obtain an overlapping sub-trajectory recognition model.

[0041] In some embodiments, the trajectory acquisition module 230 is also used to: obtain overlapping trajectory points in the pick-up trajectory of drivers in more than two historical orders; select multiple overlapping trajectory points that meet the first preset condition; and connect the selected multiple overlapping trajectory points to obtain overlapping sub-trajectories.

[0042] In some embodiments, the first preset condition includes: matching a known outline of the region of interest.

[0043] In some embodiments, the driver's pick-up trajectory includes: a driving trajectory within a preset time range before the driver picks up the passenger and after the driver picks up the passenger, or a driving trajectory within a preset length range before the driver picks up the passenger and after the driver picks up the passenger.

[0044] In some embodiments, the contour drawing module 240 is further used to: select an overlapping sub-trajectory as a starting sub-trajectory; select the overlapping sub-trajectory closest to the starting sub-trajectory as a second sub-trajectory; select overlapping sub-trajectories in sequence, so that the overlapping sub-trajectory selected each time is the overlapping sub-trajectory with the shortest distance to the overlapping sub-trajectory selected last time; connect all the selected overlapping sub-trajectories in sequence to form a closed-loop area, thereby obtaining the contour of the area of ​​interest.

[0045] In some embodiments, the pickup points associated with the region of interest include pickup points within a preset distance range from the region of interest, and / or pickup points whose names match the name of the region of interest. In some embodiments, overlapping sub-trajectories include overlapping points and / or overlapping road segments.

[0046] In some embodiments, the order acquisition module 220 further includes an order selection unit, which is used to: after acquiring at least two historical orders at each pick-up point and obtaining the driver's pick-up track in each historical order, exclude the historical orders whose pick-up track does not meet the second preset condition. In some embodiments, the second preset condition includes: there is no jump track point.

[0047] It should be understood that Figure 2 The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as carrier media such as disks, CDs or DVD-ROMs, programmable memories such as read-only memories (firmware), or data carriers such as optical or electronic signal carriers. Such codes are provided on. The system and its modules of one or more embodiments of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0048] It should be noted that the above description of the system and its modules for depicting the area of ​​interest is only for the convenience of description and does not limit this specification to the scope of the embodiments. It can be understood that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various modules or form a subsystem connected with other modules without deviating from this principle. For example, the trajectory acquisition module 230 may further include a trajectory point acquisition unit, a trajectory point selection unit and a trajectory synthesis unit. For another example, the order acquisition module 220 and the trajectory acquisition module 230 can be combined into a single module, which can be used to perform order and trajectory acquisition operations at the same time. Such variations are within the scope of protection of this specification.

[0049] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) The outline of the area of ​​interest is depicted based on the overlapping sub-trajectories of the driver's pick-up trajectories in multiple historical orders, so that the outline of the area of ​​interest can be depicted with high accuracy. (2) The overlapping sub-trajectories are obtained through the trained overlapping sub-trajectories recognition model, which has high accuracy and is conducive to improving the accuracy of the outline of the area of ​​interest; (3) The overlapping sub-trajectories are obtained by deduplicating and merging the trajectory points of the driver's pick-up trajectories of multiple historical orders, which has high accuracy and is conducive to improving the accuracy of the outline of the area of ​​interest; (4) By connecting multiple overlapping sub-trajectories, a more accurate and realistic outline of the area of ​​interest can be obtained. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0050] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0052] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment" and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0053] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0054] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, system or device to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0055] The computer program code required for the operation of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0056] In addition, unless explicitly stated in the claims, the order of processing elements and sequences, the use of alphanumeric characters, or the use of other names in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0057] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0058] Finally, it should be understood that the embodiments in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for outlining a region of interest, characterized in that: The method comprises: Select multiple boarding points related to the area of ​​interest; Obtain at least two historical orders at each pick-up point, and obtain the driver's pick-up track in each of the historical orders; Based on the pick-up trajectories of the drivers in the two or more historical orders at the same pick-up point, obtaining overlapping sub-trajectories in the two or more pick-up trajectories further includes: Splitting the driver's pick-up trajectory in each historical order into multiple sub-trajectories according to a first preset length to obtain a trajectory set for each historical order; Obtaining overlapping sub-trajectory recognition model; Inputting the trajectory set of each historical order into the overlapping sub-trajectory recognition model, and identifying the overlapping sub-trajectories in the trajectory set that overlap with each other through the overlapping sub-trajectory recognition model; and The obtaining of overlapping sub-trajectories in the two or more pick-up trajectories based on the pick-up trajectories of the drivers in the two or more historical orders at the same pick-up point further includes: obtaining the overlapping sub-trajectories by removing duplicates and merging multiple trajectory points in the two or more pick-up trajectories; Based on the overlapping sub-trajectories of the plurality of boarding points, a contour of the area of ​​interest is drawn, wherein the overlapping sub-trajectories of the plurality of boarding points are a part of the contour of the area of ​​interest.

2. The method according to claim 1, characterized in that The overlapping sub-trajectory recognition model is generated according to a training process, and the training process includes: Acquire a known outline of the region of interest; Obtain multiple historical orders at the pickup points related to the area of ​​interest, and use the driver's pickup trajectory in each historical order as a training sample; An initial model is trained based on the training samples and known contours to obtain the overlapping sub-trajectory recognition model.

3. The method according to claim 2, characterized in that Training an initial model based on the training samples and the known contours to obtain the overlapping sub-trajectory recognition model includes: Splitting the pick-up trajectory of each training sample into multiple sub-trajectories according to a second preset length to obtain a trajectory set of each training sample; Whether each sub-track in the track set of each training sample overlaps with the known contour is used as a label to classify each sub-track, and the initial model is optimized and iterated according to each sub-track and the corresponding label to obtain the overlapping sub-track recognition model.

4. The method according to claim 1, characterized in that The method further comprises: removing duplicates and merging multiple track points in the two or more pick-up tracks to obtain the overlapping sub-tracks. Obtaining overlapping track points in the pickup tracks of the drivers in the two or more historical orders; Selecting a plurality of the overlapping trajectory points that meet a first preset condition; The selected multiple overlapping trajectory points are connected to obtain the overlapping sub-trajectory.

5. The method according to claim 4, characterized in that The first preset condition includes: matching with a known outline of the region of interest.

6. The method according to claim 1, characterized in that The driver's pick-up trajectory includes: The driving trajectory within a preset time range before the driver picks up the passenger and after the driver picks up the passenger, or the driving trajectory within a preset length range before the driver picks up the passenger and after the driver picks up the passenger.

7. The method according to claim 1, characterized in that Describing the outline of the area of ​​interest based on the overlapping sub-trajectories of the plurality of boarding points includes: Selecting one of the overlapping sub-trajectories as a starting sub-trajectory; Selecting the overlapping sub-trajectory closest to the starting sub-trajectory as the second sub-trajectory; Selecting the overlapping sub-trajectories in sequence, so that the overlapping sub-trajectory selected each time is the overlapping sub-trajectory with the shortest distance from the overlapping sub-trajectory selected last time; All the selected overlapping sub-trajectories are connected in sequence to form a closed loop area, thereby obtaining the outline of the region of interest.

8. The method according to claim 1, characterized in that The boarding points associated with the area of ​​interest include boarding points whose distances from the area of ​​interest are within a preset distance range and / or boarding points whose names match the name of the area of ​​interest.

9. The method according to claim 1, characterized in that The overlapping sub-trajectories include overlapping points and / or overlapping road segments.

10. The method according to claim 1, characterized in that The method further includes: after acquiring at least two historical orders at each boarding point and obtaining the pick-up track of the driver in each of the historical orders, excluding the historical orders whose pick-up track does not meet the second preset condition.

11. The method according to claim 10, characterized in that The second preset condition includes: there is no jumping trajectory point.

12. A system for outlining a region of interest, characterized in that: The system comprises: A point selection module is used to select multiple boarding points related to the area of ​​interest; An order acquisition module is used to acquire at least two historical orders at each pick-up point and obtain the driver's pick-up track in each of the historical orders; The trajectory acquisition module is used to obtain overlapping sub-trajectories in the two or more pick-up trajectories based on the pick-up trajectories of the drivers in the two or more historical orders at the same pick-up point, further comprising: Splitting the driver's pick-up trajectory in each historical order into multiple sub-trajectories according to a first preset length to obtain a trajectory set for each historical order; Obtaining overlapping sub-trajectory recognition model; Inputting the trajectory set of each historical order into the overlapping sub-trajectory recognition model, and identifying the overlapping sub-trajectories in the trajectory set that overlap with each other through the overlapping sub-trajectory recognition model; and The obtaining of overlapping sub-trajectories in the two or more pick-up trajectories based on the pick-up trajectories of the drivers in the two or more historical orders at the same pick-up point further includes: obtaining the overlapping sub-trajectories by removing duplicates and merging multiple trajectory points in the two or more pick-up trajectories; The contour drawing module is used to draw the contour of the interest area based on the overlapping sub-trajectories of the multiple boarding points, and the overlapping sub-trajectories of the multiple boarding points are part of the contour of the interest area.

13. A device for delineating a region of interest, the device comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the operation corresponding to the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer execution instructions in the storage medium, the computer executes the method as described in any one of claims 1 to 11.

Images